start OAIServer with max_beam_width=1 for TorchSampler - #5427
Merged
netanel-haber merged 7 commits intoJun 25, 2025
Merged
Conversation
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
netanel-haber
changed the title
max_beam_width=1 for TorchSampler
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
Collaborator
Author
|
/bot run |
netanel-haber
enabled auto-merge (squash)
June 24, 2025 09:00
Collaborator
|
PR_Github #9672 [ run ] triggered by Bot |
…https://nvbugs/5355091) Signed-off-by: Netanel Haber <nhaber@nvidia.com>
Collaborator
Author
|
/bot run |
Collaborator
|
PR_Github #9677 [ run ] triggered by Bot |
Collaborator
|
PR_Github #9672 [ run ] completed with state |
Collaborator
Author
|
/bot run --disable-fail-fast |
Collaborator
|
PR_Github #9677 [ run ] completed with state |
Collaborator
|
PR_Github #9701 [ run ] triggered by Bot |
Collaborator
|
PR_Github #9701 [ run ] completed with state |
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Collaborator
|
/bot skip --comment "CI failed due to unrelated issues in main, conflicts were only in waives.txt" |
omera-nv
approved these changes
Jun 25, 2025
Collaborator
|
PR_Github #9833 [ skip ] triggered by Bot |
Collaborator
|
PR_Github #9833 [ skip ] completed with state |
dominicshanshan
pushed a commit
to dominicshanshan/TensorRT-LLM
that referenced
this pull request
Jul 9, 2025
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
dominicshanshan
pushed a commit
to dominicshanshan/TensorRT-LLM
that referenced
this pull request
Jul 10, 2025
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
dominicshanshan
pushed a commit
to dominicshanshan/TensorRT-LLM
that referenced
this pull request
Jul 10, 2025
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
dominicshanshan
pushed a commit
to dominicshanshan/TensorRT-LLM
that referenced
this pull request
Jul 10, 2025
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
dominicshanshan
pushed a commit
to dominicshanshan/TensorRT-LLM
that referenced
this pull request
Jul 10, 2025
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
dominicshanshan
pushed a commit
to dominicshanshan/TensorRT-LLM
that referenced
this pull request
Jul 11, 2025
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
dominicshanshan
pushed a commit
to dominicshanshan/TensorRT-LLM
that referenced
this pull request
Jul 11, 2025
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
dominicshanshan
pushed a commit
to dominicshanshan/TensorRT-LLM
that referenced
this pull request
Jul 11, 2025
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
TorchSampler recently added an assertion that
max_beam_width==1: https://github.com/NVIDIA/TensorRT-LLM/pull/4401/files#diff-76ef6eceb82cb64d4ea6d49fca82d42ac6c942a45ad9fc8d3ff6a9b49e3b466bR208test_openai_reasoning.pynever passed a request with beam search enabled, but did actually start pytorch backend servers withmax_beam_width=2, so the tests fail on that assertion. This pr just passesmax_beam_width=1to match the new assertion.