feat: support flashinfer mla with prefix cache #3643
Merged
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
jsun-012
reviewed
Feb 18, 2025
| @@ -1004,6 +1055,26 @@ def call_begin_forward( | |||
| custom_mask=custom_mask, | |||
| non_blocking=True, | |||
| ) | |||
| elif ( | |||
| global_config.enable_flashinfer_mla | |||
| and not global_server_args_dict["disable_radix_cache"] | |||
There was a problem hiding this comment.
@zhyncs A quick question, I feel if I want to make MTP work with flashinfer backend. During the target verify stage, it is this code block has to be run? because perfill increment computation has to use the absorb trick with flashinfer?
There was a problem hiding this comment.
The full paged version is a temporary solution. I will soon support ragged prefill + paged prefill + paged decoding. These days have been quite busy, so I haven't updated.
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Outdated suggestions cannot be applied.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.
Motivation
This version should only use
--enable-flashinfer-mla.For other LLM engines, if you refer to this PR, please include "Adapted from https://github.com/sgl-project/sglang/pull/3643/files", thank you :-)
ref #3550
Modifications
Checklist