Skip to content

[https://nvbugs/6194812][test] Update llm_perf_core.yml to require a minimum of 4 GPUs and add new performance tests #15090

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yufeiwu-nv merged 6 commits into from
Jun 9, 2026
Merged

[https://nvbugs/6194812][test] Update llm_perf_core.yml to require a minimum of 4 GPUs and add new performance tests #15090

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
e4ed8da
[https://nvbugs/6194812][test] Update llm_perf_core.yml to require a …
yufeiwu-nv Jun 8, 2026
9d695d8
Merge branch 'main' into bug
yufeiwu-nv Jun 8, 2026
e3bd38b
Merge branch 'main' into bug
yufeiwu-nv Jun 9, 2026
5ae1eca
Merge branch 'main' into bug
yufeiwu-nv Jun 9, 2026
edffb09
Merge branch 'main' into bug
yufeiwu-nv Jun 9, 2026
8c648b4
Merge branch 'main' into bug
yufeiwu-nv Jun 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion tests/integration/test_lists/qa/llm_perf_core.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ llm_perf_core:
supports_fp8: true
ranges:
system_gpu_count:
gte: 2
gte: 4
Comment thread
yufeiwu-nv marked this conversation as resolved.
tests:
- perf/test_perf.py::test_perf[llama_v3.1_8b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128]
- perf/test_perf.py::test_perf[qwen3.5_9b-bench-pytorch-bfloat16-input_output_len:128,128]
Expand All @@ -36,6 +36,10 @@ llm_perf_core:
- perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b_fp8-bench-pytorch-float8-maxnt:5000-input_output_len:5000,500-reqs:8-con:1]
- perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b_fp8-bench-pytorch-float8-input_output_len:500,2000-reqs:8-con:1]
- perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b_fp8-bench-pytorch-float8-input_output_len:1000,1000-reqs:8-con:1]
# test overlap scheduler
# con:1 paired with a small model is an intentional design choice—it amplifies host-side overhead and simplifies execution timelines to the maximum extent.
- perf/test_perf.py::test_perf[qwen3_0.6b-bench-pytorch-bfloat16-maxnt:2048-input_output_len:8000,1000-reqs:256-con:1-pp:4-gpus:4]
- perf/test_perf.py::test_perf[qwen3_30b_a3b-bench-pytorch-bfloat16-maxnt:2048-input_output_len:8000,1000-reqs:256-con:1-pp:4-gpus:4]


# 2: L40S, H100, H20, H200
Expand Down
Loading