Fix recompilations in compile due to enabled_flags #761
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
afierka-intel
force-pushed
the
dev/afierka/fix-compile-recompilations
branch
from
f10c910 to
ad61491
Compare
afierka-intel
requested review from
kzawora-intel,
madamczykhabana,
michalkuligowski,
mgawarkiewicz and
vivekgoe
as code owners
mgawarkiewicz
requested changes
Jan 31, 2025
requirements-hpu.txt
Outdated
| @@ -8,4 +8,4 @@ pandas | |||
| tabulate | |||
| setuptools>=61 | |||
| setuptools-scm>=8 | |||
| vllm-hpu-extension @ git+https://github.com/HabanaAI/vllm-hpu-extension.git@d4f37bb | |||
| vllm-hpu-extension @ git+https://github.com/HabanaAI/vllm-hpu-extension.git@dev/afierka/fix-compile-recompilations | |||
There was a problem hiding this comment.
Proper sha needed instead of a dev branch.
This PR enables loading AWQ quantized models and running weight-only quantized inference on HPU. Currently, it works only for BF16 inference due to kernel torch.ops.hpu.convert_from_uint4 not supporting FP16. Tested on TheBloke/Llama-2-70B-Chat-AWQ and worked. --------- Co-authored-by: Michał Kuligowski <[email protected]>
Dummy parameter initialization (load_format='dummy') is not working on hpu due to torch.generator not being supported. This PR fixes the issue by bypassing the generator. --------- Co-authored-by: Michał Kuligowski <[email protected]>
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Outdated suggestions cannot be applied.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.
Update vllm-hpu-extension with fix for the entitled recompilations: HabanaAI/vllm-hpu-extension#88