Kimi-K3: add mla_prefill_backend TRTLLM_RAGGED to attention-config - #718
Open
kylesayrs wants to merge 1 commit into
Open
Kimi-K3: add mla_prefill_backend TRTLLM_RAGGED to attention-config#718kylesayrs wants to merge 1 commit into
kylesayrs wants to merge 1 commit into
Conversation
Add `"mla_prefill_backend":"TRTLLM_RAGGED"` to the Blackwell `--attention-config` alongside the existing `use_prefill_query_quantization`. Also update the guide note to reflect the full config. Ref: vllm-project/vllm#50056 Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![gemini-code-assist[bot]](https://cdn.statically.io/img/avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request updates the Kimi-K3.yaml configuration file for the Moonshot AI model by adding the mla_prefill_backend parameter set to TRTLLM_RAGGED within the --attention-config argument in both the hardware overrides and the guide documentation. There are no review comments, and I have no feedback to provide.
Author
|
Just noticing https://github.com/vllm-project/vllm/pull/50181/changes. This PR can be closed once the fix lands on vLLM |
Contributor
|
yes, you are right ,this bug alreay fix by my pr #689 , but it was error merge by this pr #701 ,i have metion him , haha . @kylesayrs |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
"mla_prefill_backend":"TRTLLM_RAGGED"to the Blackwell--attention-configalongside the existinguse_prefill_query_quantization:trueRef: vllm-project/vllm#50056
Test plan
--attention-configoutput includes bothuse_prefill_query_quantizationandmla_prefill_backendin the command builder🤖 Generated with Claude Code