build(vllm-tensorizer): Compile vllm-flash-attn from source
#70
Conversation
This file contains 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
vLLM replaced their usages of the regular `flash-attn` library with their own `vllm-flash-attn` fork, which, as of right now, is fairly easy to compile. This change compiles it from source for compatibility with the `ml-containers/torch` base images. [skip ci]
sangstar
approved these changes
Jun 16, 2024
| RUN git clone --filter=blob:none --depth 1 --no-single-branch --no-checkout \ | ||
| https://github.com/vllm-project/flash-attention.git && \ | ||
| cd flash-attention && \ | ||
| git checkout "v${VLLM_FLASH_ATTN_VERSION}" && \ |
There was a problem hiding this comment.
I imagine it's safe to assume the branch names won't ever conflict here and lead to ambiguity, so it's unnecessary to explicitly do git checkout "tags/v${VLLM_FLASH_ATTN_VERSION}"?
| -v --no-cache-dir --no-build-isolation --no-deps \ | ||
| -c /tmp/constraints.txt \ | ||
| ./ && \ | ||
| pip3 uninstall -y vllm-flash-attn |
There was a problem hiding this comment.
Why is pip uninstalling here necessary?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Compile
vllm-flash-attnfrom SourcevLLM replaced their usages of the regular
flash-attnlibrary with their ownvllm-flash-attnfork in vllm-project/vllm#4686, which, as of right now, is fairly easy to compile. This change compiles it from source for compatibility with theml-containers/torchbase images.This is necessary to enable updating our
vllm-tensorizerimages to include the newest versions of vLLM.