@@ -522,6 +522,23 @@ perf/test_perf.py::test_perf[mixtral_8x22b_v0.1-bench-bfloat16-input_output_len:
522522perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128-tp:4] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
523523perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
524524perf/test_perf.py::test_perf[llama_v3.3_nemotron_49b-bench-pytorch-float8-input_output_len:128,128-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
525+ perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-float8-maxbs:1-input_output_len:1000,2000-reqs:10-con:1-ep:4-tp:8-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
526+ perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-float8-maxbs:128-maxnt:1127-input_output_len:1000,2000-reqs:5120-con:1024-ep:8-tp:8-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
527+ perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-float8-maxbs:32-input_output_len:128,128-ep:8-tp:8-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
528+ perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-streaming-float8-maxbs:32-input_output_len:128,128-ep:8-tp:8-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
529+ perf/test_perf.py::test_perf[llama_v3.1_70b-bench-bfloat16-input_output_len:512,200-quant:fp8-tp:4] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
530+ perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-cppmanager-exe-plugin_ifb-float16-input_output_len:200,2000-reqs:64-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
531+ perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-quant:int8-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
532+ perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
533+ perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:1000,1000-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
534+ perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-quant:fp8-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
535+ perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
536+ perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
537+ perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-quant:fp8-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
538+ perf/test_perf.py::test_perf[llama_v3.2_1b-bench-bfloat16-input_output_len:512,32-quant:fp8-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
539+ perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128+512,32-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
540+ perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128-loras:8-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
541+ perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-streaming-float16-input_output_len:128,128-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
525542perf/test_perf.py::test_perf[llama_v3.1_8b-cppmanager-exe-plugin_ifb-bfloat16-mp-maxbs:256-input_output_len:128,128-pp:2] SKIP (https://nvbugspro.nvidia.com/bug/5295390)
526543perf/test_perf.py::test_perf[llama_70b_sq_per_tensor-cppmanager-exe-plugin_ifb-float16-input_output_len:128,128+512,32-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5295390)
527544perf/test_perf.py::test_perf[starcoder_15.5b-cppmanager-ootb_except_mha-float16-maxbs:1-input_output_len:512,200-reqs:10-gpus:4] SKIP (https://nvbugspro.nvidia.com/bug/5295390)
0 commit comments