Enabling MOE Quantization using linear decomposition [WIP] #2043
Conversation
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2043
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Summary: This PR is a first step at optimizing moe inference using torchAO. The goal for this step is to enable existing quantization kernels and workflows to work for moe quantization by decomposing the group gemm into a sequence of unbalanced linear ops that can use the existing quantized kernels. To enable this we had to add support for quantizing these 3D tensors as well as slicing and indexing. current tests are running locally but will be added once working. currently int8wo and int8dq are working for multi and single token moe inference while int4wo is being finished up. TODO move test set into ao, move quantizable moe module code to ao test on hf model definition. Test Plan: Reviewers: Subscribers: Tasks: Tags: testing Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags:
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Outdated suggestions cannot be applied.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.
Summary: This PR is a first step at optimizing moe inference using torchAO. The goal for this step is to enable existing quantization kernels and workflows to work for moe quantization by decomposing the group gemm into a sequence of unbalanced linear ops that can use the existing quantized kernels. To enable this we had to add support for quantizing these 3D tensors as well as slicing and indexing.
current tests are running locally but will be added once working.
currently int8wo and int8dq are working for multi and single token moe inference while int4wo is being finished up.
TODO move test set into ao, move quantizable moe module code to ao test on hf model definition.
Test Plan:
Reviewers:
Subscribers:
Tasks:
Tags: