Skip to content

test: remove perf test l40s/l20 oom test cases and unwaive tests #4755

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
merged 2 commits into from
May 29, 2025
Merged

test: remove perf test l40s/l20 oom test cases and unwaive tests #4755

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c59b584
remove perf test l40s/l20 oom test cases and unwaive tests
ruodil May 26, 2025
76f8d89
fix a typo in pytorch get_model_yaml_config
ruodil May 29, 2025
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
2 changes: 1 addition & 1 deletion tests/integration/defs/perf/pytorch_model_config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
"""


def get_model_yaml_config(model_label: str, input_lens: list[int]) -> dict:
def get_model_yaml_config(model_label: str) -> dict:
"""
Return the yaml config corresponding to the model label.
Args:
Expand Down
8 changes: 4 additions & 4 deletions tests/integration/test_lists/qa/trt_llm_release_perf_cluster_test.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ trt_llm_release_perf_cluster_test:
- perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-float8-maxbs:256-input_output_len:128,128-gpus:2]
- perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-float8-maxbs:256-input_output_len:512,32-gpus:2]
- perf/test_perf.py::test_perf[llama_v2_13b-bench-float16-input_output_len:128,128-loras:8-gpus:2]
- perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:128,128-gpus:2]
- perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128-quant:fp8-gpus:2]

# Tests for systems with 4+ GPUs
Expand All @@ -34,16 +33,17 @@ trt_llm_release_perf_cluster_test:
- perf/test_perf.py::test_perf[qwen_14b_chat-bench-float16-input_output_len:128,128-gpus:4]
- perf/test_perf.py::test_perf[qwen_14b_chat-bench-float16-input_output_len:512,32-gpus:4]
- perf/test_perf.py::test_perf[starcoder_15b-bench-float16-input_output_len:512,200-gpus:4]
- perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:128,128-gpus:4]
#- perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:128,128-gpus:4]

# Tests for systems with 8+ GPUs
- condition:
ranges:
system_gpu_count:
gte: 8
tests:
- perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:128,128-gpus:8]
- perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:512,32-gpus:8]
#- perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:128,128-gpus:8]
#- perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:512,32-gpus:8]
- perf/test_perf.py::test_perf[llama_v3.3_nemotron_super_49b-bench-bfloat16-input_output_len:500,2000-quant:fp8-con:250-gpus:8]
- perf/test_perf.py::test_perf[mixtral_8x22b_v0.1-bench-float16-input_output_len:512,512-quant:fp8-tp:8]
- perf/test_perf.py::test_perf[gpt_20b-bench-float16-maxbs:8-input_output_len:128,128-reqs:80-gpus:8]
- perf/test_perf.py::test_perf[gpt_20b-bench-float16-maxbs:8-input_output_len:512,32-reqs:80-gpus:8]
Expand Down
Loading