NVIDIA
[fix] Eagle-2 LLMAPI pybind argument fix.
Description
A bug is triggered when launching Eagle-2 with LLMAPI (trtllm-serve, trtllm-bench).
Eagle-2 expects 2 arguments, --use_dynamic_tree and --dynamic_tree_max_topK.
Eagle-1 expects --eagle_choices.
Without the fix, pybind expects --eagle_choices to be not None, while the check here asserts --eagle_choice to be none when --use_dynamic_tree=True (Eagle-2 is used).
This is introduced by TRTLLM-2867, MR 8312.
Test Coverage
- examples/llm-api/llm_eagle2_decoding.py
- tests/integration/defs/test_e2e.py
- test_llmapi_example_eagle2_decoding
- tests/unittest/bindings/test_executor_bindings.py
- test_eagle_config_pickle
- tests/unittest/llmapi/test_llm.py
- test_llm_api_eagle2
GitHub Bot Help
/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...
Provide a user friendly way for developers to interact with a Jenkins server.
Run /bot [-h|--help] to print this help message.
See details below for each supported subcommand.
run [--disable-fail-fast --skip-test --stage-list "A10-1, xxx" --gpu-type "A30, H100_PCIe" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-[Post-Merge]-1, xxx"]
Launch build/test pipelines. All previously running jobs will be killed.
--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.
--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.
--stage-list "A10-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-1, xxx". Note: Does NOT update GitHub check status.
--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.
--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.
--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.
--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests. Will also run L0 pre-merge pipeline.
--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.
--extra-stage "H100_PCIe-[Post-Merge]-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-[Post-Merge]-1, xxx".
kill
kill
Kill all running builds associated with pull request.
skip
skip --comment COMMENT
Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.
reuse-pipeline
reuse-pipeline
Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.
PR_Github #3761 [ kill ] completed with state SUCCESS
Successfully killed previous jobs for commit a3ec04e
PR_Github #3764 [ kill ] completed with state SUCCESS
Successfully killed previous jobs for commit 3219e2e
PR_Github #3765 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #2666 completed with status: 'FAILURE'
PR_Github #3888 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #2758 completed with status: 'FAILURE'
PR_Github #3961 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #2807 completed with status: 'SUCCESS'
PR_Github #3984 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #3961 for commit 7781f44