Skip to content

Feature(MInference): add triton-based decoding in case flash_attn is not available - #35

Merged
Huiqiang Jiang (iofu728) merged 2 commits into
mainfrom
decoding-dev
Jul 15, 2024
Merged

Huiqiang Jiang (iofu728) merged 2 commits into
mainfrom
decoding-dev

Conversation

@liyucheng09

@liyucheng09 Yucheng Li (liyucheng09) commented Jul 13, 2024 •

Copy link
Copy Markdown
Contributor

What does this PR do?

Feature

  • Add triton-based decoding for HF mode, in case flash_attn is not available.
  • The vLLM mode stay the same as it wouldn't require flash_attn during decoding.

Bug Fixed

UnitTest

  • Passed in Local

Who can review?

Huiqiang Jiang (@iofu728)

@iofu728 Huiqiang Jiang (iofu728) changed the title add triton-based decoding in case flash_attn is not available Feature(MInference): add triton-based decoding in case flash_attn is not available Jul 15, 2024
@iofu728
Huiqiang Jiang (iofu728) deleted the decoding-dev branch July 15, 2024 05:46
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

feature feature

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Question]: Is A6000 supported?

2 participants