Open
Conversation
wuhuikx
reviewed
Mar 25, 2026
atom/models/kimi_k25.py
Outdated
|
|
||
| def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]) -> set[str]: | ||
| # load weights in plugin mode and discard passed weights generator | ||
| # here prefix is "model." because Qwen3ForCausalLM is constructed in model |
Contributor
There was a problem hiding this comment.
is this comment here right?
wuhuikx
reviewed
Mar 25, 2026
wuhuikx
reviewed
Mar 25, 2026
|
|
||
| The ATOM vLLM plugin backend keeps the standard vLLM CLI, server APIs, and general usage flow compatible with upstream vLLM. For general server options and API usage, refer to the [official vLLM documentation](https://docs.vllm.ai/en/latest/). | ||
|
|
||
| ```bash |
Contributor
There was a problem hiding this comment.
Do we need any env var here like quick allreduce to make the performance better and keep accuracy at the same time? If so we can point it out to let users to have a try, but tell them the accuracy risk.
Contributor
Author
There was a problem hiding this comment.
Yes, I think we should put such specific env var in our recipes. Maybe we can add it in another pr for all the recipes under atom_vllm, right now all the recipes just provide the basic launch cmd without providing perf-boost env var.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
This PR added the support for Kimi-K2.5-MXFP4 with vLLM oot path. Functionality and accuracy pass. The recipe is provided as well.
Technical Details
Test Plan
Test Result
Submission Checklist