Fix the KeyError when loading bloom-based models
#441
Merged
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
This was
linked to
issues
Jul 14, 2023
Closed
WoosukKwon
approved these changes
Jul 14, 2023
There was a problem hiding this comment.
Hi @HermitSun, thanks for submitting the PR! It looks good to me. I didn't consider those types of BLOOM models. TIL.
hongxiayang
pushed a commit
to hongxiayang/vllm
that referenced
this pull request
Feb 13, 2024
jikunshang
pushed a commit
to jikunshang/vllm
that referenced
this pull request
Oct 31, 2024
Implementation of multi-step scheduling. To use the feature, pass --num_scheduler_steps=[n] as a server parameter. In my tests, best results were achieved with n==64, but this will vary depending on the model. --------- Co-authored-by: Karol Damaszke <kdamaszke@habana.ai> Co-authored-by: jmaksymczuk <jmaksymczuk@habana.ai>
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Outdated suggestions cannot be applied.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.
As the issue #413 mentioned, a
KeyErrorwill be raised when loading some bloom-based models. This is because those bloom-based models provide theirlm_headin pretrained weights, which is slightly different from the behavior of original bloom models.After applying this patch, the following bloom-based models can be accelerated by vllm (tested on A100 with CUDA 11.8):
And I believe TigerResearch/tigerbot-180b-research can also be supported after solving some minor problems (issue #440).