Skip to content

Conversation

@dcampora
Copy link
Collaborator

No description provided.

Signed-off-by: Daniel Campora <[email protected]>
@dcampora
Copy link
Collaborator Author

/bot run

@dcampora
Copy link
Collaborator Author

@Funatiq this is still in a rough draft state. I'd like to see how far is it from running.

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9162 [ run ] triggered by Bot

Signed-off-by: Daniel Campora <[email protected]>
@dcampora dcampora requested a review from Funatiq June 17, 2025 08:23
@tensorrt-cicd
Copy link
Collaborator

PR_Github #9162 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #6712 completed with status: 'FAILURE'

auto const numDecodingEngineTokens = request.generatedTokensPerEngineStep;
auto const& requestIds = inputIds;
auto const inputLength = llmReq.getPromptLen();
auto const numDecodingEngineTokens = modelConfig.getMaxDecodingTokens();
Copy link
Collaborator

Choose a reason for hiding this comment

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

I think we need the previous logic here to set the correct value.

@dcampora
Copy link
Collaborator Author

Fixed in #6559 and follow ups.

@dcampora dcampora closed this Aug 11, 2025
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