network_name,perf_case_name,test_name,threshold,absolute_threshold,metric_type,perf_metric,device_subtype
"llama_v3.1_8b_instruct-bench-pytorch-float16-maxbs:512-maxnt:2048-input_output_len:128,128-reqs:8192","H100_PCIe-PyTorch-Perf-1/perf/test_perf.py::test_perf_metric_inference_time[llama_v3.1_8b_instruct-bench-pytorch-float16-maxbs:512-maxnt:2048-input_output_len:128,128-reqs:8192]","test_perf_metric_inference_time[llama_v3.1_8b_instruct-bench-pytorch-float16-maxbs:512-maxnt:2048-input_output_len:128,128-reqs:8192]",0.20,5000,INFERENCE_TIME,109007.96,
"llama_v3.1_8b_instruct-bench-pytorch-float16-maxbs:512-maxnt:2048-input_output_len:128,128-reqs:8192","H100_PCIe-PyTorch-Perf-1/perf/test_perf.py::test_perf_metric_seq_throughput[llama_v3.1_8b_instruct-bench-pytorch-float16-maxbs:512-maxnt:2048-input_output_len:128,128-reqs:8192]","test_perf_metric_seq_throughput[llama_v3.1_8b_instruct-bench-pytorch-float16-maxbs:512-maxnt:2048-input_output_len:128,128-reqs:8192]",-0.20,5,SEQ_THROUGHPUT,76.45,
"llama_v3.1_8b_instruct-bench-pytorch-float16-maxbs:512-maxnt:2048-input_output_len:128,128-reqs:8192","H100_PCIe-PyTorch-Perf-1/perf/test_perf.py::test_perf_metric_token_throughput[llama_v3.1_8b_instruct-bench-pytorch-float16-maxbs:512-maxnt:2048-input_output_len:128,128-reqs:8192]","test_perf_metric_token_throughput[llama_v3.1_8b_instruct-bench-pytorch-float16-maxbs:512-maxnt:2048-input_output_len:128,128-reqs:8192]",-0.20,500,TOKEN_THROUGHPUT,9785.75,
"llama_v3.1_8b_instruct-bench-pytorch-float16-maxbs:512-maxnt:2048-input_output_len:128,128-reqs:8192","H100_PCIe-PyTorch-Perf-1/perf/test_perf.py::test_perf_metric_kv_cache_size[llama_v3.1_8b_instruct-bench-pytorch-float16-maxbs:512-maxnt:2048-input_output_len:128,128-reqs:8192]","test_perf_metric_kv_cache_size[llama_v3.1_8b_instruct-bench-pytorch-float16-maxbs:512-maxnt:2048-input_output_len:128,128-reqs:8192]",0.20,2,KV_CACHE_SIZE,55.64,
"deepseek_r1_distill_qwen_32b-bench-_autodeploy-float16-maxbs:512-maxnt:2048-input_output_len:1024,1024","H100_PCIe-PyTorch-Perf-1/perf/test_perf.py::test_perf_metric_inference_time[deepseek_r1_distill_qwen_32b-subtype:H100_PCIe-bench-_autodeploy-float16-maxbs:512-maxnt:2048-input_output_len:1024,1024]","test_perf_metric_inference_time[deepseek_r1_distill_qwen_32b-subtype:H100_PCIe-bench-_autodeploy-float16-maxbs:512-maxnt:2048-input_output_len:1024,1024]",0.1,50,INFERENCE_TIME,1359184.5059,H100_PCIe
"deepseek_r1_distill_qwen_32b-bench-_autodeploy-float16-maxbs:512-maxnt:2048-input_output_len:1024,1024","H100_PCIe-PyTorch-Perf-1/perf/test_perf.py::test_perf_metric_kv_cache_size[deepseek_r1_distill_qwen_32b-subtype:H100_PCIe-bench-_autodeploy-float16-maxbs:512-maxnt:2048-input_output_len:1024,1024]","test_perf_metric_kv_cache_size[deepseek_r1_distill_qwen_32b-subtype:H100_PCIe-bench-_autodeploy-float16-maxbs:512-maxnt:2048-input_output_len:1024,1024]",-0.1,50,KV_CACHE_SIZE,10.92,H100_PCIe
"deepseek_r1_distill_qwen_32b-bench-_autodeploy-float16-maxbs:512-maxnt:2048-input_output_len:1024,1024","H100_PCIe-PyTorch-Perf-1/perf/test_perf.py::test_perf_metric_seq_throughput[deepseek_r1_distill_qwen_32b-subtype:H100_PCIe-bench-_autodeploy-float16-maxbs:512-maxnt:2048-input_output_len:1024,1024]","test_perf_metric_seq_throughput[deepseek_r1_distill_qwen_32b-subtype:H100_PCIe-bench-_autodeploy-float16-maxbs:512-maxnt:2048-input_output_len:1024,1024]",-0.1,10,SEQ_THROUGHPUT,0.3767,H100_PCIe
"deepseek_r1_distill_qwen_32b-bench-_autodeploy-float16-maxbs:512-maxnt:2048-input_output_len:1024,1024","H100_PCIe-PyTorch-Perf-1/perf/test_perf.py::test_perf_metric_token_throughput[deepseek_r1_distill_qwen_32b-subtype:H100_PCIe-bench-_autodeploy-float16-maxbs:512-maxnt:2048-input_output_len:1024,1024]","test_perf_metric_token_throughput[deepseek_r1_distill_qwen_32b-subtype:H100_PCIe-bench-_autodeploy-float16-maxbs:512-maxnt:2048-input_output_len:1024,1024]",-0.1,10,TOKEN_THROUGHPUT,385.7372,H100_PCIe