Skip to content

Fix [NVBUG 5219533 5220758] Fix script options for engines. #3622

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 7 commits into from
Apr 21, 2025
Merged

Fix [NVBUG 5219533 5220758] Fix script options for engines. #3622

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
d677056
Fix script options for engines.
Tracin Apr 16, 2025
a257870
Merge branch 'release/0.19' into fix_tests
Tracin Apr 17, 2025
4fac03c
Merge branch 'release/0.19' into fix_tests
Tracin Apr 18, 2025
95d89bd
Merge branch 'release/0.19' into fix_tests
Tracin Apr 18, 2025
66b750b
Merge branch 'release/0.19' into fix_tests
Tracin Apr 21, 2025
0dc5074
Merge branch 'release/0.19' into fix_tests
Tracin Apr 21, 2025
1fbcd4d
Merge branch 'release/0.19' into fix_tests
Tracin Apr 21, 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
4 changes: 2 additions & 2 deletions tests/integration/defs/examples/test_llama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4249,7 +4249,7 @@ def test_llm_llama_v3_1_1node_multi_gpus(llama_example_root, llama_model_root,
mmlu_cmd = generate_mmlu_cmd(example_root=llama_example_root,
data_dir=mmlu_dataset_root,
engine_dir=engine_dir,
tokenizer_dir=llama_model_root,
hf_model_dir=llama_model_root,
enable_chunked_prefill=True)
venv_check_call(llm_venv, mmlu_cmd)

Expand Down Expand Up @@ -4361,7 +4361,7 @@ def test_llm_llama_v3_1_2nodes_8gpus(test_type, llama_example_root,
mmlu_cmd = generate_mmlu_cmd(example_root=llama_example_root,
data_dir=mmlu_dataset_root,
engine_dir=engine_dir,
tokenizer_dir=llama_model_root,
hf_model_dir=llama_model_root,
enable_chunked_prefill=True)
venv_check_call(llm_venv, mmlu_cmd)

Expand Down
4 changes: 2 additions & 2 deletions tests/integration/defs/examples/test_mixtral.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -182,7 +182,7 @@ def test_llm_mixtral_fp8_4gpus_summary(llama_example_root,

print("Run mmlu...")
mmlu_cmd = generate_mmlu_cmd(llama_example_root,
tokenizer_dir=llm_mixtral_model_root,
hf_model_dir=llm_mixtral_model_root,
engine_dir=engine_dir,
accuracy_threshold=70,
data_dir=f"{llm_datasets_root}/mmlu")
Expand Down Expand Up @@ -247,7 +247,7 @@ def test_llm_mixtral_fp8_managed_weights_4gpus_summary(llama_example_root,

print("Run mmlu...")
mmlu_cmd = generate_mmlu_cmd(llama_example_root,
tokenizer_dir=llm_mixtral_model_root,
hf_model_dir=llm_mixtral_model_root,
engine_dir=engine_dir,
accuracy_threshold=70,
data_dir=f"{llm_datasets_root}/mmlu")
Expand Down
2 changes: 0 additions & 2 deletions tests/integration/test_lists/waives.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -417,7 +417,6 @@ examples/test_gpt.py::test_llm_gpt2_santacoder_1node_4gpus[parallel_build-enable
examples/test_llama.py::test_llm_llama_v3_1_1node_multi_gpus[enable_gemm_allreduce_plugin-llama-3.1-405b-enable_fp8] SKIP (https://nvbugs/5219532)
examples/test_llama.py::test_llm_llama_v3_1_1node_multi_gpus[enable_gemm_allreduce_plugin-llama-3.1-405b-fp8-disable_fp8] SKIP (https://nvbugs/5219532)
examples/test_llama.py::test_llm_llama_v3_1_1node_multi_gpus[disable_gemm_allreduce_plugin-llama-3.1-70b-enable_fp8] SKIP (https://nvbugs/5219532)
examples/test_llama.py::test_llm_llama_v3_1_1node_multi_gpus[enable_gemm_allreduce_plugin-llama-3.1-70b-disable_fp8] SKIP (https://nvbugs/5219533)
examples/test_medusa.py::test_llama_medusa_1gpu[llama-v2-7b-hf] SKIP (https://nvbugs/5219534)
examples/test_medusa.py::test_llama_medusa_1gpu[llama-3.2-1b] SKIP (https://nvbugs/5219534)
examples/test_medusa.py::test_llama_medusa_1gpu[llama-3.1-8b] SKIP (https://nvbugs/5219534)
Expand All @@ -431,7 +430,6 @@ examples/test_eagle.py::test_llama_eagle_1gpu[llama-3.1-8b-eagle1] SKIP (https:/
examples/test_eagle.py::test_mistral_eagle_1gpu[mistral-7b-v0.1-eagle1] SKIP (https://nvbugs/5219535)
examples/test_eagle.py::test_llama_eagle_1gpu[llama-3.1-8b-eagle2] SKIP (https://nvbugs/5219535)
examples/test_eagle.py::test_mistral_eagle_1gpu[mistral-7b-v0.1-eagle2] SKIP (https://nvbugs/5219535)
examples/test_mixtral.py::test_llm_mixtral_fp8_4gpus_summary[Mixtral-8x22B-v0.1-nb:1] SKIP (https://nvbugs/5220758)
examples/test_multimodal.py::test_llm_multimodal_general[VILA1.5-3b-pp:1-tp:1-float16-bs:8-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5214239)
examples/test_multimodal.py::test_llm_multimodal_general[VILA1.5-3b-pp:1-tp:1-float16-bs:1-cpp_e2e:True-nb:1] SKIP (https://nvbugs/5214239)
examples/test_multimodal.py::test_llm_multimodal_general[VILA1.5-3b-pp:1-tp:1-float16-bs:8-cpp_e2e:True-nb:1] SKIP (https://nvbugs/5214239)
Expand Down