8-bit packing support #1248
Merged
8-bit packing support #1248
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
Summary: Add support for 8-bit quantization for Llama in torchchat. 8-bit packing behaves exactly like 1-7 bit packing, but the implementation is slightly different: 8-bit chunks are used as-is without shifting. Reviewed By: metascroy Differential Revision: D65570988
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1248
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 2 Unrelated FailuresAs of commit 101e980 with merge base e41ca4e ( NEW FAILURE - The following job has failed:
BROKEN TRUNK - The following jobs failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D65570988 |
metascroy
approved these changes
Nov 8, 2024
jainapurva
pushed a commit
that referenced
this pull request
Nov 11, 2024
Differential Revision: D65570988 Pull Request resolved: #1248
jainapurva
pushed a commit
that referenced
this pull request
Nov 12, 2024
Differential Revision: D65570988 Pull Request resolved: #1248
sunjiweiswift
pushed a commit
to sunjiweiswift/ao
that referenced
this pull request
Nov 25, 2024
Differential Revision: D65570988 Pull Request resolved: pytorch#1248
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
…ch#1248) * Fix non-MM multiturn: Use legacy formatting * Absorb non-MM OpenAI dialog parsing into generic input parsing * Lint and docstrings
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:
Add support for 8-bit quantization for Llama in torchchat.
8-bit packing behaves exactly like 1-7 bit packing, but the implementation is slightly different: 8-bit chunks are used as-is without shifting.
Reviewed By: metascroy
Differential Revision: D65570988