x

benchmarks/benchmark_results_amd-r9700-uv+pl/RedHatAI_Qwen3-14B-FP8-dynamic_tp1_qps1.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f9e1c29aca0>, seed=0, num_prompts=180, dataset_name='sharegpt', no_stream=False, dataset_path='ShareGPT_V3_unfiltered_cleaned_split.json', no_oversample=False, skip_chat_template=False, disable_shuffle=False, custom_output_len=256, spec_bench_output_len=256, spec_bench_category=None, sonnet_input_len=550, sonnet_output_len=150, sonnet_prefix_len=200, sharegpt_output_len=None, blazedit_min_distance=0.0, blazedit_max_distance=1.0, random_input_len=1024, random_output_len=128, random_range_ratio=0.0, random_prefix_len=0, random_batch_size=1, no_reranker=False, random_mm_base_items_per_request=1, random_mm_num_mm_items_range_ratio=0.0, random_mm_limit_mm_per_prompt={'image': 255, 'video': 1}, random_mm_bucket_config={(256, 256, 1): 0.5, (720, 1280, 1): 0.5, (720, 1280, 16): 0.0}, hf_subset=None, hf_split=None, hf_name=None, hf_output_len=None, prefix_repetition_prefix_len=256, prefix_repetition_suffix_len=256, prefix_repetition_num_prefixes=10, prefix_repetition_output_len=128, label=None, backend='openai', base_url='http://127.0.0.1:8000', host='127.0.0.1', port=8000, endpoint='/v1/completions', header=None, max_concurrency=None, model='RedHatAI/Qwen3-14B-FP8-dynamic', tokenizer=None, tokenizer_mode='auto', use_beam_search=False, logprobs=None, request_rate=1.0, burstiness=1.0, trust_remote_code=True, disable_tqdm=False, num_warmups=0, profile=False, save_result=False, save_detailed=False, append_result=False, metadata=None, result_dir=None, result_filename=None, ignore_eos=False, percentile_metrics=None, metric_percentiles='99', goodput=None, request_id_prefix='bench-e4e803cf-', top_p=None, top_k=None, min_p=None, temperature=None, frequency_penalty=None, presence_penalty=None, repetition_penalty=None, common_prefix_len=None, served_model_name=None, lora_modules=None, ramp_up_strategy=None, ramp_up_start_rps=None, ramp_up_end_rps=None, ready_check_timeout_sec=600, extra_body=None)\nStarting initial single prompt test run...\nWaiting for endpoint to become up in 600 seconds\nInitial test run completed.\nStarting main benchmark run...\nTraffic request rate: 1.0\nBurstiness factor: 1.0 (Poisson process)\nMaximum request concurrency: None\ntip: install termplotlib and gnuplot to plot the metrics\n============ Serving Benchmark Result ============\nSuccessful requests:                     180       \nFailed requests:                         0         \nRequest rate configured (RPS):           1.00      \nBenchmark duration (s):                  200.63    \nTotal input tokens:                      38358     \nTotal generated tokens:                  40296     \nRequest throughput (req/s):              0.90      \nOutput token throughput (tok/s):         200.85    \nPeak output token throughput (tok/s):    350.00    \nPeak concurrent requests:                16.00     \nTotal Token throughput (tok/s):          392.04    \n---------------Time to First Token----------------\nMean TTFT (ms):                          100.59    \nMedian TTFT (ms):                        84.87     \nP99 TTFT (ms):                           217.06    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          41.46     \nMedian TPOT (ms):                        41.30     \nP99 TPOT (ms):                           45.56     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           41.46     \nMedian ITL (ms):                         40.41     \nP99 ITL (ms):                            81.46     \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700-uv+pl/RedHatAI_Qwen3-14B-FP8-dynamic_tp1_qps4.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f5f5b1aeca0>, seed=0, num_prompts=720, dataset_name='sharegpt', no_stream=False, dataset_path='ShareGPT_V3_unfiltered_cleaned_split.json', no_oversample=False, skip_chat_template=False, disable_shuffle=False, custom_output_len=256, spec_bench_output_len=256, spec_bench_category=None, sonnet_input_len=550, sonnet_output_len=150, sonnet_prefix_len=200, sharegpt_output_len=None, blazedit_min_distance=0.0, blazedit_max_distance=1.0, random_input_len=1024, random_output_len=128, random_range_ratio=0.0, random_prefix_len=0, random_batch_size=1, no_reranker=False, random_mm_base_items_per_request=1, random_mm_num_mm_items_range_ratio=0.0, random_mm_limit_mm_per_prompt={'image': 255, 'video': 1}, random_mm_bucket_config={(256, 256, 1): 0.5, (720, 1280, 1): 0.5, (720, 1280, 16): 0.0}, hf_subset=None, hf_split=None, hf_name=None, hf_output_len=None, prefix_repetition_prefix_len=256, prefix_repetition_suffix_len=256, prefix_repetition_num_prefixes=10, prefix_repetition_output_len=128, label=None, backend='openai', base_url='http://127.0.0.1:8000', host='127.0.0.1', port=8000, endpoint='/v1/completions', header=None, max_concurrency=None, model='RedHatAI/Qwen3-14B-FP8-dynamic', tokenizer=None, tokenizer_mode='auto', use_beam_search=False, logprobs=None, request_rate=4.0, burstiness=1.0, trust_remote_code=True, disable_tqdm=False, num_warmups=0, profile=False, save_result=False, save_detailed=False, append_result=False, metadata=None, result_dir=None, result_filename=None, ignore_eos=False, percentile_metrics=None, metric_percentiles='99', goodput=None, request_id_prefix='bench-d2d3278b-', top_p=None, top_k=None, min_p=None, temperature=None, frequency_penalty=None, presence_penalty=None, repetition_penalty=None, common_prefix_len=None, served_model_name=None, lora_modules=None, ramp_up_strategy=None, ramp_up_start_rps=None, ramp_up_end_rps=None, ready_check_timeout_sec=600, extra_body=None)\nStarting initial single prompt test run...\nWaiting for endpoint to become up in 600 seconds\nInitial test run completed.\nStarting main benchmark run...\nTraffic request rate: 4.0\nBurstiness factor: 1.0 (Poisson process)\nMaximum request concurrency: None\ntip: install termplotlib and gnuplot to plot the metrics\n============ Serving Benchmark Result ============\nSuccessful requests:                     720       \nFailed requests:                         0         \nRequest rate configured (RPS):           4.00      \nBenchmark duration (s):                  211.85    \nTotal input tokens:                      146694    \nTotal generated tokens:                  155558    \nRequest throughput (req/s):              3.40      \nOutput token throughput (tok/s):         734.30    \nPeak output token throughput (tok/s):    1241.00   \nPeak concurrent requests:                68.00     \nTotal Token throughput (tok/s):          1426.75   \n---------------Time to First Token----------------\nMean TTFT (ms):                          111.24    \nMedian TTFT (ms):                        89.87     \nP99 TTFT (ms):                           307.29    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          52.80     \nMedian TPOT (ms):                        52.89     \nP99 TPOT (ms):                           76.85     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           52.36     \nMedian ITL (ms):                         48.02     \nP99 ITL (ms):                            172.90    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700-uv+pl/RedHatAI_Qwen3-14B-FP8-dynamic_tp1_throughput.json

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 499.5056346299998,
+    "num_requests": 1000,
+    "total_num_tokens": 741334,
+    "requests_per_second": 2.00197941859201,
+    "tokens_per_second": 1484.1354103024892
+}

benchmarks/benchmark_results_amd-r9700-uv+pl/cpatonn_Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit_tp1_throughput.json

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 680.202111824,
+    "num_requests": 1000,
+    "total_num_tokens": 741334,
+    "requests_per_second": 1.4701512721247574,
+    "tokens_per_second": 1089.8731231693348
+}

benchmarks/benchmark_results_amd-r9700-uv+pl/meta-llama_Meta-Llama-3.1-8B-Instruct_tp1_qps1.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7fd4aef3aca0>, seed=0, num_prompts=180, dataset_name='sharegpt', no_stream=False, dataset_path='ShareGPT_V3_unfiltered_cleaned_split.json', no_oversample=False, skip_chat_template=False, disable_shuffle=False, custom_output_len=256, spec_bench_output_len=256, spec_bench_category=None, sonnet_input_len=550, sonnet_output_len=150, sonnet_prefix_len=200, sharegpt_output_len=None, blazedit_min_distance=0.0, blazedit_max_distance=1.0, random_input_len=1024, random_output_len=128, random_range_ratio=0.0, random_prefix_len=0, random_batch_size=1, no_reranker=False, random_mm_base_items_per_request=1, random_mm_num_mm_items_range_ratio=0.0, random_mm_limit_mm_per_prompt={'image': 255, 'video': 1}, random_mm_bucket_config={(256, 256, 1): 0.5, (720, 1280, 1): 0.5, (720, 1280, 16): 0.0}, hf_subset=None, hf_split=None, hf_name=None, hf_output_len=None, prefix_repetition_prefix_len=256, prefix_repetition_suffix_len=256, prefix_repetition_num_prefixes=10, prefix_repetition_output_len=128, label=None, backend='openai', base_url='http://127.0.0.1:8000', host='127.0.0.1', port=8000, endpoint='/v1/completions', header=None, max_concurrency=None, model='meta-llama/Meta-Llama-3.1-8B-Instruct', tokenizer=None, tokenizer_mode='auto', use_beam_search=False, logprobs=None, request_rate=1.0, burstiness=1.0, trust_remote_code=True, disable_tqdm=False, num_warmups=0, profile=False, save_result=False, save_detailed=False, append_result=False, metadata=None, result_dir=None, result_filename=None, ignore_eos=False, percentile_metrics=None, metric_percentiles='99', goodput=None, request_id_prefix='bench-fce2ee75-', top_p=None, top_k=None, min_p=None, temperature=None, frequency_penalty=None, presence_penalty=None, repetition_penalty=None, common_prefix_len=None, served_model_name=None, lora_modules=None, ramp_up_strategy=None, ramp_up_start_rps=None, ramp_up_end_rps=None, ready_check_timeout_sec=600, extra_body=None)\nStarting initial single prompt test run...\nWaiting for endpoint to become up in 600 seconds\nInitial test run completed.\nStarting main benchmark run...\nTraffic request rate: 1.0\nBurstiness factor: 1.0 (Poisson process)\nMaximum request concurrency: None\ntip: install termplotlib and gnuplot to plot the metrics\n============ Serving Benchmark Result ============\nSuccessful requests:                     180       \nFailed requests:                         0         \nRequest rate configured (RPS):           1.00      \nBenchmark duration (s):                  195.29    \nTotal input tokens:                      37841     \nTotal generated tokens:                  38821     \nRequest throughput (req/s):              0.92      \nOutput token throughput (tok/s):         198.79    \nPeak output token throughput (tok/s):    406.00    \nPeak concurrent requests:                13.00     \nTotal Token throughput (tok/s):          392.56    \n---------------Time to First Token----------------\nMean TTFT (ms):                          73.39     \nMedian TTFT (ms):                        61.33     \nP99 TTFT (ms):                           185.43    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          30.73     \nMedian TPOT (ms):                        30.60     \nP99 TPOT (ms):                           33.54     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           30.74     \nMedian ITL (ms):                         29.96     \nP99 ITL (ms):                            50.56     \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700-uv+pl/meta-llama_Meta-Llama-3.1-8B-Instruct_tp1_qps4.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f082b14aca0>, seed=0, num_prompts=720, dataset_name='sharegpt', no_stream=False, dataset_path='ShareGPT_V3_unfiltered_cleaned_split.json', no_oversample=False, skip_chat_template=False, disable_shuffle=False, custom_output_len=256, spec_bench_output_len=256, spec_bench_category=None, sonnet_input_len=550, sonnet_output_len=150, sonnet_prefix_len=200, sharegpt_output_len=None, blazedit_min_distance=0.0, blazedit_max_distance=1.0, random_input_len=1024, random_output_len=128, random_range_ratio=0.0, random_prefix_len=0, random_batch_size=1, no_reranker=False, random_mm_base_items_per_request=1, random_mm_num_mm_items_range_ratio=0.0, random_mm_limit_mm_per_prompt={'image': 255, 'video': 1}, random_mm_bucket_config={(256, 256, 1): 0.5, (720, 1280, 1): 0.5, (720, 1280, 16): 0.0}, hf_subset=None, hf_split=None, hf_name=None, hf_output_len=None, prefix_repetition_prefix_len=256, prefix_repetition_suffix_len=256, prefix_repetition_num_prefixes=10, prefix_repetition_output_len=128, label=None, backend='openai', base_url='http://127.0.0.1:8000', host='127.0.0.1', port=8000, endpoint='/v1/completions', header=None, max_concurrency=None, model='meta-llama/Meta-Llama-3.1-8B-Instruct', tokenizer=None, tokenizer_mode='auto', use_beam_search=False, logprobs=None, request_rate=4.0, burstiness=1.0, trust_remote_code=True, disable_tqdm=False, num_warmups=0, profile=False, save_result=False, save_detailed=False, append_result=False, metadata=None, result_dir=None, result_filename=None, ignore_eos=False, percentile_metrics=None, metric_percentiles='99', goodput=None, request_id_prefix='bench-af5860ff-', top_p=None, top_k=None, min_p=None, temperature=None, frequency_penalty=None, presence_penalty=None, repetition_penalty=None, common_prefix_len=None, served_model_name=None, lora_modules=None, ramp_up_strategy=None, ramp_up_start_rps=None, ramp_up_end_rps=None, ready_check_timeout_sec=600, extra_body=None)\nStarting initial single prompt test run...\nWaiting for endpoint to become up in 600 seconds\nInitial test run completed.\nStarting main benchmark run...\nTraffic request rate: 4.0\nBurstiness factor: 1.0 (Poisson process)\nMaximum request concurrency: None\ntip: install termplotlib and gnuplot to plot the metrics\n============ Serving Benchmark Result ============\nSuccessful requests:                     720       \nFailed requests:                         0         \nRequest rate configured (RPS):           4.00      \nBenchmark duration (s):                  204.38    \nTotal input tokens:                      145810    \nTotal generated tokens:                  152213    \nRequest throughput (req/s):              3.52      \nOutput token throughput (tok/s):         744.74    \nPeak output token throughput (tok/s):    1238.00   \nPeak concurrent requests:                53.00     \nTotal Token throughput (tok/s):          1458.16   \n---------------Time to First Token----------------\nMean TTFT (ms):                          75.15     \nMedian TTFT (ms):                        63.63     \nP99 TTFT (ms):                           179.56    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          35.83     \nMedian TPOT (ms):                        35.55     \nP99 TPOT (ms):                           48.38     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           35.60     \nMedian ITL (ms):                         33.55     \nP99 ITL (ms):                            112.07    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700-uv+pl/meta-llama_Meta-Llama-3.1-8B-Instruct_tp1_throughput.json

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 354.4166975950002,
+    "num_requests": 1000,
+    "total_num_tokens": 736330,
+    "requests_per_second": 2.821537491844479,
+    "tokens_per_second": 2077.5827013698454
+}

benchmarks/benchmark_results_amd-r9700-uv+pl/openai_gpt-oss-20b_tp1_qps1.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7fc4f7b12ca0>, seed=0, num_prompts=180, dataset_name='sharegpt', no_stream=False, dataset_path='ShareGPT_V3_unfiltered_cleaned_split.json', no_oversample=False, skip_chat_template=False, disable_shuffle=False, custom_output_len=256, spec_bench_output_len=256, spec_bench_category=None, sonnet_input_len=550, sonnet_output_len=150, sonnet_prefix_len=200, sharegpt_output_len=None, blazedit_min_distance=0.0, blazedit_max_distance=1.0, random_input_len=1024, random_output_len=128, random_range_ratio=0.0, random_prefix_len=0, random_batch_size=1, no_reranker=False, random_mm_base_items_per_request=1, random_mm_num_mm_items_range_ratio=0.0, random_mm_limit_mm_per_prompt={'image': 255, 'video': 1}, random_mm_bucket_config={(256, 256, 1): 0.5, (720, 1280, 1): 0.5, (720, 1280, 16): 0.0}, hf_subset=None, hf_split=None, hf_name=None, hf_output_len=None, prefix_repetition_prefix_len=256, prefix_repetition_suffix_len=256, prefix_repetition_num_prefixes=10, prefix_repetition_output_len=128, label=None, backend='openai', base_url='http://127.0.0.1:8000', host='127.0.0.1', port=8000, endpoint='/v1/completions', header=None, max_concurrency=None, model='openai/gpt-oss-20b', tokenizer=None, tokenizer_mode='auto', use_beam_search=False, logprobs=None, request_rate=1.0, burstiness=1.0, trust_remote_code=True, disable_tqdm=False, num_warmups=0, profile=False, save_result=False, save_detailed=False, append_result=False, metadata=None, result_dir=None, result_filename=None, ignore_eos=False, percentile_metrics=None, metric_percentiles='99', goodput=None, request_id_prefix='bench-1dd28fd7-', top_p=None, top_k=None, min_p=None, temperature=None, frequency_penalty=None, presence_penalty=None, repetition_penalty=None, common_prefix_len=None, served_model_name=None, lora_modules=None, ramp_up_strategy=None, ramp_up_start_rps=None, ramp_up_end_rps=None, ready_check_timeout_sec=600, extra_body=None)\nStarting initial single prompt test run...\nWaiting for endpoint to become up in 600 seconds\nInitial test run completed.\nStarting main benchmark run...\nTraffic request rate: 1.0\nBurstiness factor: 1.0 (Poisson process)\nMaximum request concurrency: None\ntip: install termplotlib and gnuplot to plot the metrics\n============ Serving Benchmark Result ============\nSuccessful requests:                     180       \nFailed requests:                         0         \nRequest rate configured (RPS):           1.00      \nBenchmark duration (s):                  214.85    \nTotal input tokens:                      38756     \nTotal generated tokens:                  39194     \nRequest throughput (req/s):              0.84      \nOutput token throughput (tok/s):         182.43    \nPeak output token throughput (tok/s):    308.00    \nPeak concurrent requests:                19.00     \nTotal Token throughput (tok/s):          362.82    \n---------------Time to First Token----------------\nMean TTFT (ms):                          115.51    \nMedian TTFT (ms):                        108.55    \nP99 TTFT (ms):                           235.09    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          53.14     \nMedian TPOT (ms):                        53.86     \nP99 TPOT (ms):                           69.03     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           53.53     \nMedian ITL (ms):                         52.81     \nP99 ITL (ms):                            120.56    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700-uv+pl/openai_gpt-oss-20b_tp1_qps4.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f58e6eeeca0>, seed=0, num_prompts=720, dataset_name='sharegpt', no_stream=False, dataset_path='ShareGPT_V3_unfiltered_cleaned_split.json', no_oversample=False, skip_chat_template=False, disable_shuffle=False, custom_output_len=256, spec_bench_output_len=256, spec_bench_category=None, sonnet_input_len=550, sonnet_output_len=150, sonnet_prefix_len=200, sharegpt_output_len=None, blazedit_min_distance=0.0, blazedit_max_distance=1.0, random_input_len=1024, random_output_len=128, random_range_ratio=0.0, random_prefix_len=0, random_batch_size=1, no_reranker=False, random_mm_base_items_per_request=1, random_mm_num_mm_items_range_ratio=0.0, random_mm_limit_mm_per_prompt={'image': 255, 'video': 1}, random_mm_bucket_config={(256, 256, 1): 0.5, (720, 1280, 1): 0.5, (720, 1280, 16): 0.0}, hf_subset=None, hf_split=None, hf_name=None, hf_output_len=None, prefix_repetition_prefix_len=256, prefix_repetition_suffix_len=256, prefix_repetition_num_prefixes=10, prefix_repetition_output_len=128, label=None, backend='openai', base_url='http://127.0.0.1:8000', host='127.0.0.1', port=8000, endpoint='/v1/completions', header=None, max_concurrency=None, model='openai/gpt-oss-20b', tokenizer=None, tokenizer_mode='auto', use_beam_search=False, logprobs=None, request_rate=4.0, burstiness=1.0, trust_remote_code=True, disable_tqdm=False, num_warmups=0, profile=False, save_result=False, save_detailed=False, append_result=False, metadata=None, result_dir=None, result_filename=None, ignore_eos=False, percentile_metrics=None, metric_percentiles='99', goodput=None, request_id_prefix='bench-2f4f4694-', top_p=None, top_k=None, min_p=None, temperature=None, frequency_penalty=None, presence_penalty=None, repetition_penalty=None, common_prefix_len=None, served_model_name=None, lora_modules=None, ramp_up_strategy=None, ramp_up_start_rps=None, ramp_up_end_rps=None, ready_check_timeout_sec=600, extra_body=None)\nStarting initial single prompt test run...\nWaiting for endpoint to become up in 600 seconds\nInitial test run completed.\nStarting main benchmark run...\nTraffic request rate: 4.0\nBurstiness factor: 1.0 (Poisson process)\nMaximum request concurrency: None\ntip: install termplotlib and gnuplot to plot the metrics\n============ Serving Benchmark Result ============\nSuccessful requests:                     720       \nFailed requests:                         0         \nRequest rate configured (RPS):           4.00      \nBenchmark duration (s):                  236.39    \nTotal input tokens:                      145540    \nTotal generated tokens:                  152178    \nRequest throughput (req/s):              3.05      \nOutput token throughput (tok/s):         643.77    \nPeak output token throughput (tok/s):    1024.00   \nPeak concurrent requests:                92.00     \nTotal Token throughput (tok/s):          1259.45   \n---------------Time to First Token----------------\nMean TTFT (ms):                          850.20    \nMedian TTFT (ms):                        141.29    \nP99 TTFT (ms):                           5024.92   \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          71.13     \nMedian TPOT (ms):                        71.70     \nP99 TPOT (ms):                           89.98     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           70.90     \nMedian ITL (ms):                         66.80     \nP99 ITL (ms):                            157.64    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700-uv+pl/openai_gpt-oss-20b_tp1_throughput.json

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 602.7616506659997,
+    "num_requests": 1000,
+    "total_num_tokens": 738792,
+    "requests_per_second": 1.6590305619063292,
+    "tokens_per_second": 1225.6785068919007
+}