Use kernels from the kernel hub #2988
Open
+7,198
−258
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
Narsil
reviewed
Feb 3, 2025
server/text_generation_server/layers/compressed_tensors/w8a8_int.py
Outdated
Show resolved
Hide resolved
danieldk
force-pushed
the
kernel-hub
branch
3 times, most recently
from
e01578d to
27decc5
Compare
danieldk
commented
Feb 5, 2025
| @@ -90,7 +90,7 @@ mkShell { | |||
|
|
|||
| postVenvCreation = '' | |||
| unset SOURCE_DATE_EPOCH | |||
| ( cd server ; python -m pip install --no-dependencies -e . ) | |||
| ( cd server ; python -m pip install --no-build-isolation --no-dependencies -e . ) | |||
There was a problem hiding this comment.
This is to avoid downloading torch as a build dependency (since without build isolation it is used from the environment).
danieldk
commented
Feb 5, 2025
| @@ -230,3 +232,111 @@ def _pack_weight( | |||
| moe_weight.perm[expert] = weight.perm | |||
|
|
|||
| return moe_weight | |||
|
|
|||
|
|
|||
| def fused_marlin_moe( | |||
There was a problem hiding this comment.
I'd like to keep moe on the kernel hub as close to vLLM as possible, so moved this with our own extensions here.
danieldk
commented
Feb 5, 2025
| @@ -146,3 +159,110 @@ def _load_expert_weights_row( | |||
| assert all_weight is not None | |||
|
|
|||
| return all_weight | |||
|
|
|||
|
|
|||
| def fused_moe( | |||
There was a problem hiding this comment.
I'd like to keep moe on the kernel hub as close to vLLM as possible, so moved this with our own extensions here.
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Outdated suggestions cannot be applied.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.
What does this PR do?
Use hub kernels for paged attention, MoE, and quantization (Marlin, cutlass, etc.).
Fixes # (issue)
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.