1023 lines
118 KiB
Plaintext
1023 lines
118 KiB
Plaintext
|
WARNING 12-10 08:45:12 [argparse_utils.py:195] With `vllm serve`, you should provide the model as a positional argument or in a config file instead of via the `--model` option. The `--model` option will be removed in v0.13.
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:45:12 [api_server.py:1772] vLLM API server version 0.12.0
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:45:12 [utils.py:253] non-default args: {'model_tag': 'openai/gpt-oss-20b', 'host': '127.0.0.1', 'model': 'openai/gpt-oss-20b', 'trust_remote_code': True, 'max_model_len': 16384, 'max_num_seqs': 32}
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:45:19 [model.py:637] Resolved architecture: GptOssForCausalLM
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m
|
||
|
|
Parse safetensors files: 0%| | 0/3 [00:00<?, ?it/s]
|
||
|
|
Parse safetensors files: 33%|███▎ | 1/3 [00:00<00:00, 3.73it/s]
|
||
|
|
Parse safetensors files: 100%|██████████| 3/3 [00:00<00:00, 11.17it/s]
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:45:20 [model.py:1750] Using max model len 16384
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:45:20 [scheduler.py:228] Chunked prefill is enabled with max_num_batched_tokens=2048.
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:45:20 [config.py:274] Overriding max cuda graph capture size to 1024 for performance.
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:29 [core.py:93] Initializing a V1 LLM engine (v0.12.0) with config: model='openai/gpt-oss-20b', speculative_config=None, tokenizer='openai/gpt-oss-20b', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.bfloat16, max_seq_len=16384, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, disable_custom_all_reduce=False, quantization=mxfp4, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='openai_gptoss', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01), seed=0, served_model_name=openai/gpt-oss-20b, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'level': None, 'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::kda_attention', 'vllm::sparse_attn_indexer'], 'compile_mm_encoder': False, 'compile_sizes': [], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512, 528, 544, 560, 576, 592, 608, 624, 640, 656, 672, 688, 704, 720, 736, 752, 768, 784, 800, 816, 832, 848, 864, 880, 896, 912, 928, 944, 960, 976, 992, 1008, 1024], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'eliminate_noops': True, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False}, 'max_cudagraph_capture_size': 1024, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>}, 'local_cache_dir': None}
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:30 [parallel_state.py:1200] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://172.17.0.2:59799 backend=nccl
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:30 [parallel_state.py:1408] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank 0
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:30 [gpu_model_runner.py:3467] Starting to load model openai/gpt-oss-20b...
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:31 [cuda.py:411] Using TRITON_ATTN attention backend out of potential backends: ['TRITON_ATTN']
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:31 [layer.py:379] Enabled separate cuda stream for MoE shared_experts
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:31 [mxfp4.py:162] Using Marlin backend
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m
|
||
|
|
Loading safetensors checkpoint shards: 0% Completed | 0/3 [00:00<?, ?it/s]
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m
|
||
|
|
Loading safetensors checkpoint shards: 33% Completed | 1/3 [00:00<00:01, 1.40it/s]
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m
|
||
|
|
Loading safetensors checkpoint shards: 67% Completed | 2/3 [00:01<00:00, 1.23it/s]
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m
|
||
|
|
Loading safetensors checkpoint shards: 100% Completed | 3/3 [00:02<00:00, 1.18it/s]
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m
|
||
|
|
Loading safetensors checkpoint shards: 100% Completed | 3/3 [00:02<00:00, 1.21it/s]
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:34 [default_loader.py:308] Loading weights took 2.57 seconds
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m WARNING 12-10 08:45:34 [marlin_utils_fp4.py:226] Your GPU does not have native support for FP4 computation but FP4 quantization is being used. Weight-only FP4 compression will be used leveraging the Marlin kernel. This may degrade performance for compute-heavy workloads.
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:35 [gpu_model_runner.py:3549] Model loading took 13.7194 GiB memory and 4.366336 seconds
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:41 [backends.py:655] Using cache directory: /root/.cache/vllm/torch_compile_cache/9e0957b12c/rank_0_0/backbone for vLLM's torch.compile
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:41 [backends.py:715] Dynamo bytecode transform time: 5.94 s
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:42 [backends.py:257] Cache the graph for dynamic shape for later use
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:50 [backends.py:288] Compiling a graph for dynamic shape takes 7.71 s
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:54 [monitor.py:34] torch.compile takes 13.66 s in total
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:55 [gpu_worker.py:359] Available KV cache memory: 7.12 GiB
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:55 [kv_cache_utils.py:1286] GPU KV cache size: 155,584 tokens
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:45:55 [kv_cache_utils.py:1291] Maximum concurrency for 16,384 tokens per request: 16.75x
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 0%| | 0/83 [00:00<?, ?it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 1%| | 1/83 [00:00<00:12, 6.72it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 2%|▏ | 2/83 [00:00<00:11, 6.98it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 4%|▎ | 3/83 [00:00<00:11, 6.93it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 5%|▍ | 4/83 [00:00<00:11, 6.89it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 6%|▌ | 5/83 [00:00<00:11, 6.96it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 7%|▋ | 6/83 [00:00<00:10, 7.02it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 8%|▊ | 7/83 [00:01<00:10, 7.05it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 10%|▉ | 8/83 [00:01<00:10, 7.09it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 11%|█ | 9/83 [00:01<00:10, 7.24it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 12%|█▏ | 10/83 [00:01<00:09, 7.33it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 13%|█▎ | 11/83 [00:01<00:09, 7.43it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 14%|█▍ | 12/83 [00:01<00:09, 7.48it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 16%|█▌ | 13/83 [00:01<00:09, 7.57it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 17%|█▋ | 14/83 [00:01<00:09, 7.65it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 18%|█▊ | 15/83 [00:02<00:08, 7.74it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 19%|█▉ | 16/83 [00:02<00:08, 7.77it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 20%|██ | 17/83 [00:02<00:08, 7.89it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 22%|██▏ | 18/83 [00:02<00:08, 8.00it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 23%|██▎ | 19/83 [00:02<00:07, 8.13it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 24%|██▍ | 20/83 [00:02<00:07, 8.16it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 25%|██▌ | 21/83 [00:02<00:07, 8.25it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 27%|██▋ | 22/83 [00:02<00:07, 8.36it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 28%|██▊ | 23/83 [00:03<00:07, 8.40it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 29%|██▉ | 24/83 [00:03<00:06, 8.49it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 30%|███ | 25/83 [00:03<00:06, 8.66it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 31%|███▏ | 26/83 [00:03<00:06, 8.85it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 33%|███▎ | 27/83 [00:03<00:06, 9.01it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 34%|███▎ | 28/83 [00:03<00:05, 9.17it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 35%|███▍ | 29/83 [00:03<00:05, 9.39it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 36%|███▌ | 30/83 [00:03<00:05, 9.55it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 37%|███▋ | 31/83 [00:03<00:05, 9.58it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 39%|███▊ | 32/83 [00:03<00:05, 9.66it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 41%|████ | 34/83 [00:04<00:04, 10.20it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 43%|████▎ | 36/83 [00:04<00:04, 10.52it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 46%|████▌ | 38/83 [00:04<00:04, 10.91it/s]
|
||
|
|
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 48%|████▊ | 40/83 [00:04<00:03, 11.04it/s
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m
|
||
|
|
Capturing CUDA graphs (decode, FULL): 0%| | 0/7 [00:00<?, ?it/s]
|
||
|
|
Capturing CUDA graphs (decode, FULL): 14%|█▍ | 1/7 [00:01<00:09, 1.66s/it]
|
||
|
|
Capturing CUDA graphs (decode, FULL): 29%|██▊ | 2/7 [00:02<00:06, 1.23s/it]
|
||
|
|
Capturing CUDA graphs (decode, FULL): 57%|█████▋ | 4/7 [00:04<00:03, 1.06s/it]
|
||
|
|
Capturing CUDA graphs (decode, FULL): 86%|████████▌ | 6/7 [00:04<00:00, 1.68it/s]
|
||
|
|
Capturing CUDA graphs (decode, FULL): 100%|██████████| 7/7 [00:06<00:00, 1.22it/s]
|
||
|
|
Capturing CUDA graphs (decode, FULL): 100%|██████████| 7/7 [00:06<00:00, 1.14it/s]
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:46:09 [gpu_model_runner.py:4466] Graph capturing finished in 14 secs, took 0.63 GiB
|
||
|
|
[0;36m(EngineCore_DP0 pid=1960)[0;0m INFO 12-10 08:46:09 [core.py:254] init engine (profile, create kv cache, warmup model) took 33.89 seconds
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:11 [api_server.py:1520] Supported tasks: ['generate']
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m WARNING 12-10 08:46:11 [serving_responses.py:215] For gpt-oss, we ignore --enable-auto-tool-choice and always enable tool use.
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [api_server.py:1847] Starting vLLM API server 0 on http://127.0.0.1:8000
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:38] Available routes are:
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /openapi.json, Methods: HEAD, GET
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /docs, Methods: HEAD, GET
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /docs/oauth2-redirect, Methods: HEAD, GET
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /redoc, Methods: HEAD, GET
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /health, Methods: GET
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /load, Methods: GET
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /pause, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /resume, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /is_paused, Methods: GET
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /tokenize, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /detokenize, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v1/models, Methods: GET
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /version, Methods: GET
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v1/responses, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v1/responses/{response_id}, Methods: GET
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v1/responses/{response_id}/cancel, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v1/messages, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v1/chat/completions, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v1/completions, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v1/audio/transcriptions, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v1/audio/translations, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /scale_elastic_ep, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /is_scaling_elastic_ep, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /inference/v1/generate, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /ping, Methods: GET
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /ping, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /invocations, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /metrics, Methods: GET
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /classify, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v1/embeddings, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /score, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v1/score, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /rerank, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v1/rerank, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /v2/rerank, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:14 [launcher.py:46] Route: /pooling, Methods: POST
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: Started server process [1916]
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: Waiting for application startup.
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: Application startup complete.
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:38426 - "GET /v1/models HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45150 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45150 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45150 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45164 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45176 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45178 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45180 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45164 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:45 [loggers.py:236] Engine 000: Avg prompt throughput: 83.7 tokens/s, Avg generation throughput: 161.4 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45178 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45178 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45150 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45180 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45178 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45180 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45150 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:46:55 [loggers.py:236] Engine 000: Avg prompt throughput: 132.9 tokens/s, Avg generation throughput: 170.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45180 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45178 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:60260 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45180 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45178 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:60260 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45180 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:47:05 [loggers.py:236] Engine 000: Avg prompt throughput: 214.2 tokens/s, Avg generation throughput: 178.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:60260 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:60260 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45180 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:60260 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45180 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:60260 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:60260 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:47:15 [loggers.py:236] Engine 000: Avg prompt throughput: 290.4 tokens/s, Avg generation throughput: 150.2 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:60260 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45180 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45568 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45570 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45570 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45568 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45570 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:60260 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:47:25 [loggers.py:236] Engine 000: Avg prompt throughput: 269.8 tokens/s, Avg generation throughput: 203.2 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45180 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45568 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45570 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:60260 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45570 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:60260 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45568 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45570 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45568 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:47:35 [loggers.py:236] Engine 000: Avg prompt throughput: 240.4 tokens/s, Avg generation throughput: 190.5 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:60260 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45180 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45568 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45570 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45180 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45570 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45568 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45570 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46558 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45570 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46572 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46572 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:47:45 [loggers.py:236] Engine 000: Avg prompt throughput: 476.2 tokens/s, Avg generation throughput: 317.8 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46558 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46558 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58204 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58208 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:47:55 [loggers.py:236] Engine 000: Avg prompt throughput: 261.0 tokens/s, Avg generation throughput: 80.7 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.6%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58208 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58228 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58228 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58208 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46558 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:48:05 [loggers.py:236] Engine 000: Avg prompt throughput: 183.3 tokens/s, Avg generation throughput: 405.1 tokens/s, Running: 3 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58204 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58228 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58208 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58228 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46558 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:48:15 [loggers.py:236] Engine 000: Avg prompt throughput: 406.7 tokens/s, Avg generation throughput: 341.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46558 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:48:25 [loggers.py:236] Engine 000: Avg prompt throughput: 128.6 tokens/s, Avg generation throughput: 145.8 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:48:35 [loggers.py:236] Engine 000: Avg prompt throughput: 108.9 tokens/s, Avg generation throughput: 202.3 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.2%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:36434 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:36434 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:48:45 [loggers.py:236] Engine 000: Avg prompt throughput: 245.0 tokens/s, Avg generation throughput: 197.2 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:36434 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:36434 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:36434 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58244 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:36434 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:48:55 [loggers.py:236] Engine 000: Avg prompt throughput: 170.6 tokens/s, Avg generation throughput: 359.9 tokens/s, Running: 3 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.6%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58240 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:36434 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:46580 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58224 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:49:05 [loggers.py:236] Engine 000: Avg prompt throughput: 104.4 tokens/s, Avg generation throughput: 94.7 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50982 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50982 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50982 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50984 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50986 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50994 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50994 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:49:15 [loggers.py:236] Engine 000: Avg prompt throughput: 109.5 tokens/s, Avg generation throughput: 97.9 tokens/s, Running: 3 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50986 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57742 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50982 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57746 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50986 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50982 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57742 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50994 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:49:25 [loggers.py:236] Engine 000: Avg prompt throughput: 131.5 tokens/s, Avg generation throughput: 265.6 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50994 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50982 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58134 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58134 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50982 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50994 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58134 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58138 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58152 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58156 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58134 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50994 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58134 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:49:35 [loggers.py:236] Engine 000: Avg prompt throughput: 244.3 tokens/s, Avg generation throughput: 227.6 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.9%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58134 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:50982 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58152 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:49:45 [loggers.py:236] Engine 000: Avg prompt throughput: 75.3 tokens/s, Avg generation throughput: 141.8 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:49:55 [loggers.py:236] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:50:05 [loggers.py:236] Engine 000: Avg prompt throughput: 637.9 tokens/s, Avg generation throughput: 452.2 tokens/s, Running: 14 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.4%, Prefix cache hit rate: 13.5%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:50:15 [loggers.py:236] Engine 000: Avg prompt throughput: 1216.5 tokens/s, Avg generation throughput: 790.4 tokens/s, Running: 13 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.0%, Prefix cache hit rate: 31.2%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:50:25 [loggers.py:236] Engine 000: Avg prompt throughput: 863.1 tokens/s, Avg generation throughput: 948.4 tokens/s, Running: 20 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.5%, Prefix cache hit rate: 39.6%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:50:35 [loggers.py:236] Engine 000: Avg prompt throughput: 666.2 tokens/s, Avg generation throughput: 849.1 tokens/s, Running: 7 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.0%, Prefix cache hit rate: 44.8%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47062 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47062 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:50:45 [loggers.py:236] Engine 000: Avg prompt throughput: 814.9 tokens/s, Avg generation throughput: 790.6 tokens/s, Running: 20 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.9%, Prefix cache hit rate: 46.1%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47062 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:50:55 [loggers.py:236] Engine 000: Avg prompt throughput: 962.0 tokens/s, Avg generation throughput: 944.4 tokens/s, Running: 15 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.9%, Prefix cache hit rate: 41.2%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47062 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:51:05 [loggers.py:236] Engine 000: Avg prompt throughput: 821.8 tokens/s, Avg generation throughput: 817.4 tokens/s, Running: 15 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.5%, Prefix cache hit rate: 37.7%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:51:15 [loggers.py:236] Engine 000: Avg prompt throughput: 576.8 tokens/s, Avg generation throughput: 793.2 tokens/s, Running: 22 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.4%, Prefix cache hit rate: 35.6%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52892 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52896 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52912 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52920 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52892 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52892 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:51:25 [loggers.py:236] Engine 000: Avg prompt throughput: 828.7 tokens/s, Avg generation throughput: 1155.7 tokens/s, Running: 23 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.8%, Prefix cache hit rate: 33.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52896 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52912 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52920 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57392 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:51:35 [loggers.py:236] Engine 000: Avg prompt throughput: 650.3 tokens/s, Avg generation throughput: 873.2 tokens/s, Running: 13 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.7%, Prefix cache hit rate: 31.2%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40874 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52912 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52920 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57440 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52892 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:45194 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57436 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40810 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40820 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52896 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57408 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52892 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:51:45 [loggers.py:236] Engine 000: Avg prompt throughput: 1187.4 tokens/s, Avg generation throughput: 715.4 tokens/s, Running: 15 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.4%, Prefix cache hit rate: 29.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52892 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:51:55 [loggers.py:236] Engine 000: Avg prompt throughput: 418.6 tokens/s, Avg generation throughput: 704.1 tokens/s, Running: 13 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.9%, Prefix cache hit rate: 28.1%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52892 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52920 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:52:05 [loggers.py:236] Engine 000: Avg prompt throughput: 801.0 tokens/s, Avg generation throughput: 703.3 tokens/s, Running: 16 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.1%, Prefix cache hit rate: 26.6%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52920 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52920 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:53704 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:53714 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:53704 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52892 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:53704 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:53714 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:52:15 [loggers.py:236] Engine 000: Avg prompt throughput: 953.1 tokens/s, Avg generation throughput: 801.5 tokens/s, Running: 18 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.0%, Prefix cache hit rate: 25.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52920 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:53714 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52892 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52920 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:52:25 [loggers.py:236] Engine 000: Avg prompt throughput: 702.7 tokens/s, Avg generation throughput: 656.4 tokens/s, Running: 14 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.7%, Prefix cache hit rate: 23.9%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52920 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:53704 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:53714 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52892 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:53704 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:53704 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57416 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:52:35 [loggers.py:236] Engine 000: Avg prompt throughput: 677.7 tokens/s, Avg generation throughput: 768.8 tokens/s, Running: 16 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.7%, Prefix cache hit rate: 22.9%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52920 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40798 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47128 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:53704 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52892 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:53714 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47084 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57430 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57458 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57418 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40782 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52920 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52930 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40870 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO 12-10 08:52:45 [loggers.py:236] Engine 000: Avg prompt throughput: 656.2 tokens/s, Avg generation throughput: 813.9 tokens/s, Running: 13 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.8%, Prefix cache hit rate: 22.0%
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40844 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47112 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57388 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40832 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:52920 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47070 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:57452 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:58938 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40884 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:40856 - "POST /v1/completions HTTP/1.1" 200 OK
|
||
|
|
[0;36m(APIServer pid=1916)[0;0m INFO: 127.0.0.1:47096 - "POST /v1/completions HTTP/1.1" 200 OK
|