Skip to content

Conversation

@ixlmar
Copy link
Collaborator

@ixlmar ixlmar commented May 20, 2025

fix: update usage of TRTLLMSampler.beam_width

Description

This fixes a regression introduced when beam_width was refactored from a class member variable to a class member function. In local testing, this regression prevented usage of PyTorchConfig(enable_trtllm_sampler=True).

Test Coverage

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.

@ixlmar ixlmar force-pushed the fix/trtllm-sampler-beam-width branch from bff28e8 to 609e1bc Compare May 20, 2025 14:20
@ixlmar ixlmar requested review from dcampora and netanel-haber May 20, 2025 14:24
@ixlmar
Copy link
Collaborator Author

ixlmar commented May 20, 2025

/bot run

@ixlmar ixlmar marked this pull request as ready for review May 20, 2025 14:29
@tensorrt-cicd
Copy link
Collaborator

PR_Github #5884 [ run ] triggered by Bot

@ixlmar
Copy link
Collaborator Author

ixlmar commented May 20, 2025

Issue already addressed by #4473

@ixlmar ixlmar closed this May 20, 2025
@tensorrt-cicd
Copy link
Collaborator

PR_Github #5884 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #4310 completed with status: 'FAILURE'

logits = model_outputs["logits"].reshape((batch_size, beam_width, -1))

self.setup_sampler_step(scheduled_requests.context_requests)
self.setup_sampler_step(scheduled_requests)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please note that this change changes behaviour. In the previous incarnation, only the context requests were passed. In the latter, both context and gen requests are passed.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Indeed. I was relying on the argument type annotation, which probably should be RequestList.

@ixlmar ixlmar deleted the fix/trtllm-sampler-beam-width branch May 27, 2025 07:33
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants