Add new backends & support multi-modal LM #142
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
kentang-mit
approved these changes
Feb 23, 2024
|
@ys-2020 how much inference speed improvements for batch=1 and GEMV by introducing this new kernel? |
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Outdated suggestions cannot be applied.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.
We add new backend kernels (W4A16 GEMM / GEMV) for better inference speed. We also support multi-modal models (VILA and LLaVA) in this PR.
Note: We changed the weight packing format in this PR. Please re-quantize the model or use
tinychat/offline-weight-repacker.pyto repack the old awq checkpoints.