Supporting tensor parallelism for int8 weight only quant #939
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/939
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit b113eda with merge base 64719d5 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jerryzh168
changed the title
Summary: following https://github.com/pytorch/ao/blob/main/tutorials/developer_api_guide/tensor_parallel.py we can support tensor parallelism for int8 weight only quant, this is needed for torchchat Test Plan: python test/dtypes/test_affine_quantized_tensor_parallel.py Reviewers: Subscribers: Tasks: Tags:
jerryzh168
force-pushed
the
aqt_tensor_parallel
branch
from
41fc6f9 to
7139466
Compare
kwen2501
approved these changes
Sep 27, 2024
This was referenced Oct 1, 2024
melvinebenezer
pushed a commit
to melvinebenezer/ao
that referenced
this pull request
Oct 3, 2024
* [WIP] Supporting tensor parallelism for int8 weight only quant Summary: following https://github.com/pytorch/ao/blob/main/tutorials/developer_api_guide/tensor_parallel.py we can support tensor parallelism for int8 weight only quant, this is needed for torchchat Test Plan: python test/dtypes/test_affine_quantized_tensor_parallel.py Reviewers: Subscribers: Tasks: Tags: * implement tp for aqt * fixes * import fix * remove cpu test * fix * fix * fix test * device * change transpose impl * Skip compiled TP test for torch version < 2.5 * version util * fix * fix version --------- Co-authored-by: Ke Wen <[email protected]>
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
…s empty (pytorch#939) Skip error if sdk/cmdline-tools/latest/* is empty
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:
following https://github.com/pytorch/ao/blob/main/tutorials/developer_api_guide/tensor_parallel.py we can support tensor parallelism for int8 weight only quant, this is needed for torchchat
Test Plan:
python test/dtypes/test_affine_quantized_tensor_parallel.py
Reviewers:
Subscribers:
Tasks:
Tags: