Add an environment variable to support calling flaggems attention interface - #283
Closed
ZenithJoyH wants to merge 0 commit into
Closed
Add an environment variable to support calling flaggems attention interface#283ZenithJoyH wants to merge 0 commit into
ZenithJoyH wants to merge 0 commit into
Conversation
| raise ValueError("use_sparse=True requires use_mla=True.") | ||
| # TODO: return "vllm_fl.dispatch.backends.flaggems.impl.attention.AttentionFLBackend" | ||
|
|
||
| use_flaggems_attn = os.environ.get( |
Collaborator
There was a problem hiding this comment.
add device check , if nvidia or ppu, use_flaggems_attn=true
| Returns: | ||
| Fully qualified class path string | ||
| """ | ||
| import os |
Collaborator
There was a problem hiding this comment.
move import to the top of file
| use_flaggems_attn = True | ||
|
|
||
| if use_flaggems_attn: | ||
| return "vllm_fl.dispatch.backends.flaggems.impl.attention.AttentionFLBackend" |
Collaborator
There was a problem hiding this comment.
add log to show call flaggems attn
3 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR Category
OP
PR Type
Description
Add an environment variable(VLLM_FL_USE_FLAGGEMS_ATTN) to support calling flaggems attention interface
Related Issues
Changes
Add an environment variable(VLLM_FL_USE_FLAGGEMS_ATTN) to support calling flaggems attention interface
Testing
在NV和平头哥上设置VLLM_FL_USE_FLAGGEMS_ATTN=1进行了minicpm5模型的精度测试无精度问题（math_500&mmlu_pro_other）
Checklist