support wInt4aFp8 for moe #518
Open
Conversation
This file contains hidden or 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
Collaborator
brian-dellabetta
left a comment
brian-dellabetta
left a comment
There was a problem hiding this comment.
Hi @Wangzheee , thanks for the contribution. Can you explain why this is needed, and why the PackedQuantizationCompressor can't be used instead? Perhaps it can subclass it to reduce redundant logic
| @BaseCompressor.register(name=CompressionFormat.int4_quantized.value) | ||
| class Int4PackedQuantizationCompressor(BaseQuantizationCompressor): | ||
| """ | ||
| Compresses a quantized model by packing every eight 4-bit weights into an int8 |
Collaborator
There was a problem hiding this comment.
Suggested change
| Compresses a quantized model by packing every eight 4-bit weights into an int8 | |
| Compresses a quantized model by packing every two 4-bit weights into an int8 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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 Int4PackedQuantizationCompressor for support wInt4aFp8
with llm-compressor PR: https://github.com/vllm-project/llm-compressor/pull/2027
with sglang PR: https://github.com/sgl-project/sglang/pull/11701