x

benchmarks/benchmark_results_amd-r9700/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 0x7f84fa08eca0>, 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-84569f25-', 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):                  203.97    \nTotal input tokens:                      38358     \nTotal generated tokens:                  40296     \nRequest throughput (req/s):              0.88      \nOutput token throughput (tok/s):         197.56    \nPeak output token throughput (tok/s):    330.00    \nPeak concurrent requests:                18.00     \nTotal Token throughput (tok/s):          385.62    \n---------------Time to First Token----------------\nMean TTFT (ms):                          108.91    \nMedian TTFT (ms):                        95.15     \nP99 TTFT (ms):                           230.11    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          47.90     \nMedian TPOT (ms):                        47.66     \nP99 TPOT (ms):                           53.10     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           47.94     \nMedian ITL (ms):                         46.64     \nP99 ITL (ms):                            85.76     \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/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 0x7f5366d42ca0>, 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-a714d425-', 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):                  217.26    \nTotal input tokens:                      146694    \nTotal generated tokens:                  155585    \nRequest throughput (req/s):              3.31      \nOutput token throughput (tok/s):         716.13    \nPeak output token throughput (tok/s):    1152.00   \nPeak concurrent requests:                77.00     \nTotal Token throughput (tok/s):          1391.33   \n---------------Time to First Token----------------\nMean TTFT (ms):                          186.47    \nMedian TTFT (ms):                        105.59    \nP99 TTFT (ms):                           1603.40   \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          59.68     \nMedian TPOT (ms):                        59.91     \nP99 TPOT (ms):                           84.43     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           59.35     \nMedian ITL (ms):                         54.32     \nP99 ITL (ms):                            190.63    \n==================================================\n"
+}

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

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 544.9470995769998,
+    "num_requests": 1000,
+    "total_num_tokens": 741334,
+    "requests_per_second": 1.8350405035208417,
+    "tokens_per_second": 1360.3779166371198
+}

benchmarks/benchmark_results_amd-r9700/RedHatAI_gemma-3-12b-it-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 0x7fde305aeca0>, 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/gemma-3-12b-it-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-a3fea59e-', 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):                  196.99    \nTotal input tokens:                      40429     \nTotal generated tokens:                  38821     \nRequest throughput (req/s):              0.91      \nOutput token throughput (tok/s):         197.07    \nPeak output token throughput (tok/s):    340.00    \nPeak concurrent requests:                15.00     \nTotal Token throughput (tok/s):          402.31    \n---------------Time to First Token----------------\nMean TTFT (ms):                          104.59    \nMedian TTFT (ms):                        82.18     \nP99 TTFT (ms):                           271.75    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          38.86     \nMedian TPOT (ms):                        38.92     \nP99 TPOT (ms):                           50.07     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           38.20     \nMedian ITL (ms):                         32.74     \nP99 ITL (ms):                            86.49     \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/RedHatAI_gemma-3-12b-it-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 0x7f83b1b0aca0>, 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/gemma-3-12b-it-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-f36abb16-', 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):                  241.29    \nTotal input tokens:                      158086    \nTotal generated tokens:                  152183    \nRequest throughput (req/s):              2.98      \nOutput token throughput (tok/s):         630.70    \nPeak output token throughput (tok/s):    896.00    \nPeak concurrent requests:                152.00    \nTotal Token throughput (tok/s):          1285.86   \n---------------Time to First Token----------------\nMean TTFT (ms):                          12436.56  \nMedian TTFT (ms):                        17115.90  \nP99 TTFT (ms):                           24750.51  \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          84.04     \nMedian TPOT (ms):                        85.32     \nP99 TPOT (ms):                           115.82    \n---------------Inter-token Latency----------------\nMean ITL (ms):                           83.72     \nMedian ITL (ms):                         75.54     \nP99 ITL (ms):                            261.14    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/RedHatAI_gemma-3-12b-it-FP8-dynamic_tp1_throughput.json

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 878.6614384089999,
+    "num_requests": 1000,
+    "total_num_tokens": 755432,
+    "requests_per_second": 1.1380947840509639,
+    "tokens_per_second": 859.7532189051877
+}

benchmarks/benchmark_results_amd-r9700/RedHatAI_gemma-3-12b-it-FP8-dynamic_tp2_qps1.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f87f9f3eca0>, 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/gemma-3-12b-it-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-a1348ed0-', 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):                  190.66    \nTotal input tokens:                      40429     \nTotal generated tokens:                  39127     \nRequest throughput (req/s):              0.94      \nOutput token throughput (tok/s):         205.22    \nPeak output token throughput (tok/s):    422.00    \nPeak concurrent requests:                11.00     \nTotal Token throughput (tok/s):          417.26    \n---------------Time to First Token----------------\nMean TTFT (ms):                          89.11     \nMedian TTFT (ms):                        64.29     \nP99 TTFT (ms):                           255.75    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          22.00     \nMedian TPOT (ms):                        21.60     \nP99 TPOT (ms):                           28.81     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           21.91     \nMedian ITL (ms):                         20.88     \nP99 ITL (ms):                            45.88     \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/RedHatAI_gemma-3-12b-it-FP8-dynamic_tp2_qps4.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f8e7772aca0>, 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/gemma-3-12b-it-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-370f24dd-', 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):                  203.05    \nTotal input tokens:                      158086    \nTotal generated tokens:                  153200    \nRequest throughput (req/s):              3.55      \nOutput token throughput (tok/s):         754.51    \nPeak output token throughput (tok/s):    1152.00   \nPeak concurrent requests:                78.00     \nTotal Token throughput (tok/s):          1533.08   \n---------------Time to First Token----------------\nMean TTFT (ms):                          222.29    \nMedian TTFT (ms):                        103.65    \nP99 TTFT (ms):                           2503.58   \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          54.74     \nMedian TPOT (ms):                        55.60     \nP99 TPOT (ms):                           83.43     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           54.25     \nMedian ITL (ms):                         49.31     \nP99 ITL (ms):                            204.91    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/RedHatAI_gemma-3-12b-it-FP8-dynamic_tp2_throughput.json

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 569.8341109329999,
+    "num_requests": 1000,
+    "total_num_tokens": 755432,
+    "requests_per_second": 1.7548966985543941,
+    "tokens_per_second": 1325.705122782343
+}

benchmarks/benchmark_results_amd-r9700/RedHatAI_gemma-3-27b-it-FP8-dynamic_tp2_qps1.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7fab82852ca0>, 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/gemma-3-27b-it-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-eb2c00d0-', 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):                  202.25    \nTotal input tokens:                      40429     \nTotal generated tokens:                  39398     \nRequest throughput (req/s):              0.89      \nOutput token throughput (tok/s):         194.80    \nPeak output token throughput (tok/s):    308.00    \nPeak concurrent requests:                17.00     \nTotal Token throughput (tok/s):          394.70    \n---------------Time to First Token----------------\nMean TTFT (ms):                          135.44    \nMedian TTFT (ms):                        102.54    \nP99 TTFT (ms):                           390.74    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          47.24     \nMedian TPOT (ms):                        46.60     \nP99 TPOT (ms):                           56.08     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           47.00     \nMedian ITL (ms):                         45.58     \nP99 ITL (ms):                            140.61    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/RedHatAI_gemma-3-27b-it-FP8-dynamic_tp2_qps4.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f310eb62ca0>, 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/gemma-3-27b-it-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-eb0dc17a-', 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):                  320.24    \nTotal input tokens:                      158086    \nTotal generated tokens:                  152563    \nRequest throughput (req/s):              2.25      \nOutput token throughput (tok/s):         476.40    \nPeak output token throughput (tok/s):    608.00    \nPeak concurrent requests:                304.00    \nTotal Token throughput (tok/s):          970.05    \n---------------Time to First Token----------------\nMean TTFT (ms):                          52928.91  \nMedian TTFT (ms):                        59992.28  \nP99 TTFT (ms):                           104765.35 \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          61.40     \nMedian TPOT (ms):                        60.27     \nP99 TPOT (ms):                           90.17     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           60.58     \nMedian ITL (ms):                         53.74     \nP99 ITL (ms):                            244.74    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/RedHatAI_gemma-3-27b-it-FP8-dynamic_tp2_throughput.json

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 767.3010607799997,
+    "num_requests": 1000,
+    "total_num_tokens": 755432,
+    "requests_per_second": 1.303269408989804,
+    "tokens_per_second": 984.5314161719857
+}

benchmarks/benchmark_results_amd-r9700/cpatonn_Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit_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 0x7f575fb42ca0>, 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='cpatonn/Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit', 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-1e0af39c-', 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):                  198.24    \nTotal input tokens:                      38358     \nTotal generated tokens:                  40157     \nRequest throughput (req/s):              0.91      \nOutput token throughput (tok/s):         202.57    \nPeak output token throughput (tok/s):    311.00    \nPeak concurrent requests:                18.00     \nTotal Token throughput (tok/s):          396.07    \n---------------Time to First Token----------------\nMean TTFT (ms):                          120.83    \nMedian TTFT (ms):                        107.92    \nP99 TTFT (ms):                           215.44    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          45.17     \nMedian TPOT (ms):                        44.69     \nP99 TPOT (ms):                           56.10     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           44.94     \nMedian ITL (ms):                         42.97     \nP99 ITL (ms):                            110.51    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/cpatonn_Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit_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 0x7f193f9faca0>, 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='cpatonn/Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit', 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-5a7df568-', 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):                  249.37    \nTotal input tokens:                      146694    \nTotal generated tokens:                  153158    \nRequest throughput (req/s):              2.89      \nOutput token throughput (tok/s):         614.17    \nPeak output token throughput (tok/s):    832.00    \nPeak concurrent requests:                168.00    \nTotal Token throughput (tok/s):          1202.42   \n---------------Time to First Token----------------\nMean TTFT (ms):                          14118.91  \nMedian TTFT (ms):                        18607.33  \nP99 TTFT (ms):                           31435.29  \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          88.10     \nMedian TPOT (ms):                        90.68     \nP99 TPOT (ms):                           104.28    \n---------------Inter-token Latency----------------\nMean ITL (ms):                           87.93     \nMedian ITL (ms):                         84.69     \nP99 ITL (ms):                            190.09    \n==================================================\n"
+}

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

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 726.8079903329999,
+    "num_requests": 1000,
+    "total_num_tokens": 741334,
+    "requests_per_second": 1.3758792051004176,
+    "tokens_per_second": 1019.986034633913
+}

benchmarks/benchmark_results_amd-r9700/cpatonn_Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit_tp2_qps1.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f6885e56ca0>, 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='cpatonn/Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit', 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-df1894e5-', 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):                  191.60    \nTotal input tokens:                      38358     \nTotal generated tokens:                  39514     \nRequest throughput (req/s):              0.94      \nOutput token throughput (tok/s):         206.23    \nPeak output token throughput (tok/s):    361.00    \nPeak concurrent requests:                15.00     \nTotal Token throughput (tok/s):          406.42    \n---------------Time to First Token----------------\nMean TTFT (ms):                          74.14     \nMedian TTFT (ms):                        66.00     \nP99 TTFT (ms):                           145.78    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          28.00     \nMedian TPOT (ms):                        28.14     \nP99 TPOT (ms):                           35.12     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           27.59     \nMedian ITL (ms):                         27.66     \nP99 ITL (ms):                            54.69     \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/cpatonn_Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit_tp2_qps4.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7fb8a2696ca0>, 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='cpatonn/Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit', 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-e434292b-', 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):                  203.64    \nTotal input tokens:                      146694    \nTotal generated tokens:                  153347    \nRequest throughput (req/s):              3.54      \nOutput token throughput (tok/s):         753.01    \nPeak output token throughput (tok/s):    1160.00   \nPeak concurrent requests:                65.00     \nTotal Token throughput (tok/s):          1473.36   \n---------------Time to First Token----------------\nMean TTFT (ms):                          93.13     \nMedian TTFT (ms):                        87.23     \nP99 TTFT (ms):                           181.31    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          47.81     \nMedian TPOT (ms):                        47.62     \nP99 TPOT (ms):                           61.13     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           47.43     \nMedian ITL (ms):                         44.70     \nP99 ITL (ms):                            109.90    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/cpatonn_Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit_tp2_throughput.json

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 449.04138348200104,
+    "num_requests": 1000,
+    "total_num_tokens": 741334,
+    "requests_per_second": 2.2269662369327774,
+    "tokens_per_second": 1650.9257882903235
+}

benchmarks/benchmark_results_amd-r9700/cpatonn_Qwen3-Next-80B-A3B-Instruct-AWQ-4bit_tp2_qps1.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f98e81ceca0>, 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='cpatonn/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit', 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-b53e2ad8-', 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):                  196.26    \nTotal input tokens:                      38358     \nTotal generated tokens:                  38404     \nRequest throughput (req/s):              0.92      \nOutput token throughput (tok/s):         195.68    \nPeak output token throughput (tok/s):    304.00    \nPeak concurrent requests:                18.00     \nTotal Token throughput (tok/s):          391.12    \n---------------Time to First Token----------------\nMean TTFT (ms):                          519.96    \nMedian TTFT (ms):                        124.31    \nP99 TTFT (ms):                           10120.96  \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          44.04     \nMedian TPOT (ms):                        42.30     \nP99 TPOT (ms):                           57.88     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           43.67     \nMedian ITL (ms):                         40.54     \nP99 ITL (ms):                            125.33    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/cpatonn_Qwen3-Next-80B-A3B-Instruct-AWQ-4bit_tp2_qps4.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f4ab18f6ca0>, 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='cpatonn/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit', 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-72f2dd3c-', 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):                  351.46    \nTotal input tokens:                      146694    \nTotal generated tokens:                  148389    \nRequest throughput (req/s):              2.05      \nOutput token throughput (tok/s):         422.20    \nPeak output token throughput (tok/s):    544.00    \nPeak concurrent requests:                369.00    \nTotal Token throughput (tok/s):          839.58    \n---------------Time to First Token----------------\nMean TTFT (ms):                          72209.01  \nMedian TTFT (ms):                        79268.59  \nP99 TTFT (ms):                           146128.91 \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          71.26     \nMedian TPOT (ms):                        71.50     \nP99 TPOT (ms):                           93.20     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           70.85     \nMedian ITL (ms):                         62.03     \nP99 ITL (ms):                            206.26    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/cpatonn_Qwen3-Next-80B-A3B-Instruct-AWQ-4bit_tp2_throughput.json

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 1089.8343978980001,
+    "num_requests": 1000,
+    "total_num_tokens": 741334,
+    "requests_per_second": 0.9175705978162676,
+    "tokens_per_second": 680.226281561525
+}

benchmarks/benchmark_results_amd-r9700/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 0x7f532a48eca0>, 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-df39931f-', 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):                  198.49    \nTotal input tokens:                      37841     \nTotal generated tokens:                  38900     \nRequest throughput (req/s):              0.91      \nOutput token throughput (tok/s):         195.98    \nPeak output token throughput (tok/s):    365.00    \nPeak concurrent requests:                16.00     \nTotal Token throughput (tok/s):          386.62    \n---------------Time to First Token----------------\nMean TTFT (ms):                          80.34     \nMedian TTFT (ms):                        69.07     \nP99 TTFT (ms):                           180.64    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          37.10     \nMedian TPOT (ms):                        37.08     \nP99 TPOT (ms):                           40.10     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           37.10     \nMedian ITL (ms):                         36.27     \nP99 ITL (ms):                            58.47     \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/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 0x7f081ef62ca0>, 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-ba51e591-', 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:                     719       \nFailed requests:                         1         \nRequest rate configured (RPS):           4.00      \nBenchmark duration (s):                  209.75    \nTotal input tokens:                      145579    \nTotal generated tokens:                  150640    \nRequest throughput (req/s):              3.43      \nOutput token throughput (tok/s):         718.18    \nPeak output token throughput (tok/s):    1259.00   \nPeak concurrent requests:                58.00     \nTotal Token throughput (tok/s):          1412.23   \n---------------Time to First Token----------------\nMean TTFT (ms):                          85.92     \nMedian TTFT (ms):                        75.54     \nP99 TTFT (ms):                           188.35    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          42.81     \nMedian TPOT (ms):                        42.63     \nP99 TPOT (ms):                           54.28     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           42.63     \nMedian ITL (ms):                         40.26     \nP99 ITL (ms):                            125.13    \n==================================================\n"
+}

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

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 410.0767225319996,
+    "num_requests": 1000,
+    "total_num_tokens": 736330,
+    "requests_per_second": 2.438568065569649,
+    "tokens_per_second": 1795.5908237208996
+}

benchmarks/benchmark_results_amd-r9700/meta-llama_Meta-Llama-3.1-8B-Instruct_tp2_qps1.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f4b1de6aca0>, 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-073f047f-', 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):                  190.90    \nTotal input tokens:                      37841     \nTotal generated tokens:                  38766     \nRequest throughput (req/s):              0.94      \nOutput token throughput (tok/s):         203.07    \nPeak output token throughput (tok/s):    413.00    \nPeak concurrent requests:                11.00     \nTotal Token throughput (tok/s):          401.29    \n---------------Time to First Token----------------\nMean TTFT (ms):                          58.57     \nMedian TTFT (ms):                        47.42     \nP99 TTFT (ms):                           140.81    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          21.86     \nMedian TPOT (ms):                        21.74     \nP99 TPOT (ms):                           23.96     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           21.82     \nMedian ITL (ms):                         21.46     \nP99 ITL (ms):                            32.13     \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/meta-llama_Meta-Llama-3.1-8B-Instruct_tp2_qps4.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f791efdeca0>, 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-2ef19409-', 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):                  196.59    \nTotal input tokens:                      145810    \nTotal generated tokens:                  151842    \nRequest throughput (req/s):              3.66      \nOutput token throughput (tok/s):         772.38    \nPeak output token throughput (tok/s):    1274.00   \nPeak concurrent requests:                43.00     \nTotal Token throughput (tok/s):          1514.08   \n---------------Time to First Token----------------\nMean TTFT (ms):                          57.73     \nMedian TTFT (ms):                        49.35     \nP99 TTFT (ms):                           135.16    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          25.29     \nMedian TPOT (ms):                        24.90     \nP99 TPOT (ms):                           34.94     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           25.09     \nMedian ITL (ms):                         23.53     \nP99 ITL (ms):                            78.49     \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/meta-llama_Meta-Llama-3.1-8B-Instruct_tp2_throughput.json

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 269.04666597899995,
+    "num_requests": 1000,
+    "total_num_tokens": 736330,
+    "requests_per_second": 3.7168273257028708,
+    "tokens_per_second": 2736.811464734795
+}

benchmarks/benchmark_results_amd-r9700/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 0x7fa6fac76ca0>, 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-84df0cbe-', 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):                  217.42    \nTotal input tokens:                      38756     \nTotal generated tokens:                  39194     \nRequest throughput (req/s):              0.83      \nOutput token throughput (tok/s):         180.27    \nPeak output token throughput (tok/s):    290.00    \nPeak concurrent requests:                20.00     \nTotal Token throughput (tok/s):          358.52    \n---------------Time to First Token----------------\nMean TTFT (ms):                          129.43    \nMedian TTFT (ms):                        121.63    \nP99 TTFT (ms):                           431.05    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          61.28     \nMedian TPOT (ms):                        61.83     \nP99 TPOT (ms):                           74.53     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           61.80     \nMedian ITL (ms):                         59.99     \nP99 ITL (ms):                            129.94    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/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 0x7fdfa3a9eca0>, 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-4ea75820-', 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):                  246.91    \nTotal input tokens:                      145540    \nTotal generated tokens:                  152007    \nRequest throughput (req/s):              2.92      \nOutput token throughput (tok/s):         615.63    \nPeak output token throughput (tok/s):    896.00    \nPeak concurrent requests:                109.00    \nTotal Token throughput (tok/s):          1205.06   \n---------------Time to First Token----------------\nMean TTFT (ms):                          4078.97   \nMedian TTFT (ms):                        3857.18   \nP99 TTFT (ms):                           10112.65  \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          78.49     \nMedian TPOT (ms):                        79.02     \nP99 TPOT (ms):                           93.10     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           78.52     \nMedian ITL (ms):                         74.18     \nP99 ITL (ms):                            163.52    \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/openai_gpt-oss-20b_tp1_throughput.json

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 674.5005297629996,
+    "num_requests": 1000,
+    "total_num_tokens": 738792,
+    "requests_per_second": 1.4825785242175744,
+    "tokens_per_second": 1095.31715306375
+}

benchmarks/benchmark_results_amd-r9700/openai_gpt-oss-20b_tp2_qps1.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": true,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f16adb6eca0>, 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-7a645b9b-', 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):                  199.44    \nTotal input tokens:                      38756     \nTotal generated tokens:                  38779     \nRequest throughput (req/s):              0.90      \nOutput token throughput (tok/s):         194.44    \nPeak output token throughput (tok/s):    395.00    \nPeak concurrent requests:                14.00     \nTotal Token throughput (tok/s):          388.76    \n---------------Time to First Token----------------\nMean TTFT (ms):                          75.40     \nMedian TTFT (ms):                        67.78     \nP99 TTFT (ms):                           192.76    \n-----Time per Output Token (excl. 1st token)------\nMean TPOT (ms):                          28.60     \nMedian TPOT (ms):                        28.16     \nP99 TPOT (ms):                           41.84     \n---------------Inter-token Latency----------------\nMean ITL (ms):                           29.20     \nMedian ITL (ms):                         25.34     \nP99 ITL (ms):                            71.24     \n==================================================\n"
+}

benchmarks/benchmark_results_amd-r9700/openai_gpt-oss-20b_tp2_qps4.0_latency.json

@@ -0,0 +1,4 @@
+{
+  "success": false,
+  "raw_output": "Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x7f64d27beca0>, 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-c0304eb1-', 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)\nERROR 12-09 20:35:02 [repo_utils.py:65] Error retrieving file list: 502 Server Error: Bad Gateway for url: https://huggingface.co/api/models/openai/gpt-oss-20b/tree/main?recursive=True&expand=False, retrying 1 of 2\nERROR 12-09 20:35:04 [repo_utils.py:63] Error retrieving file list: 502 Server Error: Bad Gateway for url: https://huggingface.co/api/models/openai/gpt-oss-20b/tree/main?recursive=True&expand=False\nERROR 12-09 20:35:04 [repo_utils.py:128] Error retrieving file list. Please ensure your `model_name_or_path``repo_type`, `token` and `revision` arguments are correctly set. Returning an empty list.\n"
+}

benchmarks/benchmark_results_amd-r9700/openai_gpt-oss-20b_tp2_throughput.json

@@ -0,0 +1,7 @@
+{
+    "elapsed_time": 393.24469268199937,
+    "num_requests": 1000,
+    "total_num_tokens": 738792,
+    "requests_per_second": 2.542945953522781,
+    "tokens_per_second": 1878.7081268950026
+}