[Spec] Remove dead kernel params; fix stale comment in trtllm_mla#25010
Merged
Conversation
- fla/kda.py: drop num_accepted_tokens kwarg that is never wired into the kernel - mamba_state_scatter_triton: drop unused total_requests kernel param (kernel reads pid_req from program_id, bounds check uses src_req_size) - trtllm_mla_backend.pad_draft_extend_query_kernel: fix comment that said 'accept length' for what is actually a seq_lens load
hnyls2002
requested review from
Fridge003,
HaiShaw,
Qiaolin-Yu,
hebiao064,
ispobock,
merrymercy,
yizhang2077 and
yuan-luo
as code owners
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
…ernel Production kernel _fused_mamba_state_scatter_with_mask_kernel uses step_indices_raw_ptr + total_requests; the test fixtures used accepted_steps + request_number, which is the same concept under different names. Rename for local clarity / future grep-ability.
Collaborator
Author
|
/rerun-failed-ci |
Collaborator
Author
|
/rerun-test test_mamba_state_scatter_triton.py test_kda_kernels.py |
Contributor
|
🚀 🚀 |
LucQueen
pushed a commit
to LucQueen/sglang
that referenced
this pull request
May 12, 2026
xjpang
pushed a commit
to xjpang/sglang
that referenced
this pull request
May 13, 2026
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Three independent cleanups in spec / attention scope:
fla/kda.py: dropnum_accepted_tokenskwarg fromfused_recurrent_kda_fwd. The param is never read inside the function (the only inner reference is commented out), and the lone caller hardcodesnum_accepted_tokens=None.mamba_state_scatter_triton._fused_mamba_state_scatter_with_mask_kernel: drop the unusedtotal_requestskernel param.pid_reqcomes fromtl.program_id, bounds checks usesrc_req_size/dst_req_size; the param is loaded but never read.trtllm_mla_backend.pad_draft_extend_query_kernel: fix two stale comments that said 'accept length(s)' for what is actually aseq_lens_qload. Comment-only.No behavior change. Splits out the trivial cleanup portion from #24081.