[https://nvbugs/6225775][fix] Fix spec count graph#15212
Open
chuangz0 wants to merge 2 commits into
Open
Conversation
…on (NVIDIA#14537) Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
CUDA graph warmup can capture speculative sampling without the generated-token count frequency-penalty path when warmup requests have no frequency penalty. Later RWLT GPT-OSS disagg requests replay that graph with frequency_penalty and prompt_ignore_length, so repeated generated tokens are not penalized. Add speculative logits penalty CUDA ops, preserve sequence-slot count state across CUDA graph metadata/replay, append accepted tokens back into count state, and gate forced graph count capture to the disaggregated generation role by default. Validation: python3 -m py_compile on modified Python modules; git diff --cached --check; GPT-OSS disagg original NVBug config ran 8 total auto-gating runs with >10k=0 and 16K/length=0.
chuangz0
requested review from
byshiue and
cascade812
and removed request for
a team
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
@coderabbitai summary
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
If PR introduces API changes, an appropriate PR label is added - either
api-compatibleorapi-breaking. Forapi-breaking, includeBREAKINGin the PR title.Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
To see a list of available CI bot commands, please comment
/bot help.