Conversation
Signed-off-by: smedhe <smedhe@qti.qualcomm.com>
Signed-off-by: smedhe <smedhe@qti.qualcomm.com>
…king Signed-off-by: smedhe <smedhe@qti.qualcomm.com>
Signed-off-by: smedhe <smedhe@qti.qualcomm.com>
vbaddi
requested changes
Sep 16, 2026
| or mode == BlockingMode.HQKV | ||
| or mode == BlockingMode.BHQKV | ||
| ) and supports_blocked_kv(past_key_value) | ||
| if mode == BlockingMode.KV_BATCH_FOLD: |
Contributor
There was a problem hiding this comment.
@smedhe batch fold is also verified? also MOE EP is verified? for Prefill only mode?
There were blocking techniques specific to prefill online softmax too, those are also verified?
| kv_block_size = -(-ctx_len // num_kv_blocks) | ||
| if hasattr(module, "config"): | ||
| mask_dtype = module.config.torch_dtype | ||
| mask_dtype = module.config.dtype |
Contributor
There was a problem hiding this comment.
@quic-rishinr will this affect the AI200 model generations?
vbaddi
changed the base branch from
main
to
quic-enable-blocking-for-weightfree
September 16, 2026 19:06
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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