Use revision when downloading the quantization config file #2697
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
Pernekhan
force-pushed
the
quant-config-use-revision
branch
from
5b2e064 to
723b61a
Compare
zhuohan123
approved these changes
Feb 1, 2024
hongxiayang
pushed a commit
to hongxiayang/vllm
that referenced
this pull request
Feb 13, 2024
…ect#2697) Co-authored-by: Pernekhan Utemuratov <pernekhan@deepinfra.com>
alexm-redhat
pushed a commit
to neuralmagic/nm-vllm
that referenced
this pull request
Feb 13, 2024
…ect#2697) Co-authored-by: Pernekhan Utemuratov <pernekhan@deepinfra.com>
xjpang
pushed a commit
to xjpang/vllm
that referenced
this pull request
Feb 20, 2024
…ect#2697) Co-authored-by: Pernekhan Utemuratov <pernekhan@deepinfra.com>
xjpang
pushed a commit
to xjpang/vllm
that referenced
this pull request
Feb 22, 2024
…ect#2697) Co-authored-by: Pernekhan Utemuratov <pernekhan@deepinfra.com>
xjpang
pushed a commit
to xjpang/vllm
that referenced
this pull request
Mar 4, 2024
…ect#2697) Co-authored-by: Pernekhan Utemuratov <pernekhan@deepinfra.com>
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Outdated suggestions cannot be applied.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.
Problem
When using quantization, it's not respecting the model's revision that was passed from the arguments.
It tries to fetch from the latest main branch instead.
Testing
Consider these two revisions for testing:
When you pass
--model notstoic/pygmalion-13b-4bit-128g --revision 5f7a136b834d0cfdd6906e43dfe2182ce165e65c --download-dir=/data --quantization gptqit will start working as it tries to fetch from the same revision, not from the latest main