kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][ci] parallelize unit tests of auto deploy in B200 (#7291)

Browse Source 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
This commit is contained in:
QI JUN 2025-08-27 22:32:11 +08:00 committed by GitHub
parent 8dc62ffac4
commit d09add5ede
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/integration/defs/agg_unit_mem_df.csv
View File

@ -103,5 +103,7 @@ unittest/trt/model/test_mamba.py,NVIDIA H100,10,
"unittest/trt/attention/test_gpt_attention.py -k ""xqa_generic""",NVIDIA L40,3,
unittest/_torch/speculative,NVIDIA Graphics Device,4,B200 Bring Up Board
unittest/_torch/thop,NVIDIA Graphics Device,32,B200 Bring Up Board
"unittest/_torch/auto_deploy/unit/singlegpu -k ""not test_trtllm_bench_backend_comparison""",NVIDIA Graphics Device,4,B200 Bring Up Board
unittest/_torch/speculative,NVIDIA B200,4,
unittest/_torch/thop,NVIDIA B200,32,
"unittest/_torch/auto_deploy/unit/singlegpu -k ""not test_trtllm_bench_backend_comparison""",NVIDIA B200,4,

1 unittest_case_name gpu parallel_factor comment
103 unittest/trt/attention/test_gpt_attention.py -k "xqa_generic" NVIDIA L40 3
104 unittest/_torch/speculative NVIDIA Graphics Device 4 B200 Bring Up Board
105 unittest/_torch/thop NVIDIA Graphics Device 32 B200 Bring Up Board
106 unittest/_torch/auto_deploy/unit/singlegpu -k "not test_trtllm_bench_backend_comparison" NVIDIA Graphics Device 4 B200 Bring Up Board
107 unittest/_torch/speculative NVIDIA B200 4
108 unittest/_torch/thop NVIDIA B200 32
109 unittest/_torch/auto_deploy/unit/singlegpu -k "not test_trtllm_bench_backend_comparison" NVIDIA B200 4