(flashinfer-ai#12)

Co-authored-by: wangbo134 <wangbo134@meituan.com>

…g→functional-API migration (NOT committed)

Captures the analysis surfaced 2026-04-30 around an alternative
to the medium-term thin-adapter refactor: migrate SGLang from
`CuteDslMoEWrapper.run(...)` to `cute_dsl_fused_moe_nvfp4(...)`
directly, then deprecate the wrapper. Lee maintains both fi and
SGLang sides, so the cross-project coordination cost normally
faced by such a migration is essentially zero — but the question
of whether to pursue is not decided.

Heavily caveated as a future consideration that **may not be
pursued**. Priority is explicitly lower than the existing PR queue
(PR flashinfer-ai#3171, flashinfer-ai#3198, bucket-cap-fix, prealloc-fix, convergence) and
Phase 1 in follow-up flashinfer-ai#11.

Captured for two reasons:

1. The 5-minute pass on SGLang's `flashinfer_cutedsl.py:ensure_cutedsl_wrapper()`
   surfaces specific gaps in the functional API that would need to
   be closed before any migration. Documenting them here means
   future-Lee (or future-someone) doesn't have to re-derive them.

2. The thin-adapter refactor and the deprecate-the-wrapper migration
   are alternatives, not sequential. If migration is pursued, the
   thin-adapter is redundant. If it's not, the thin-adapter is the
   recommended cleanup. The relationship needed to be on the record.

Captured fi-side prerequisites (if pursued):

- Add `moe_sort_buffers`, `gemm1_out`, `gemm1_out_scale` parameters
  to `cute_dsl_fused_moe_nvfp4`. Forward to `_moe_core_impl` (which
  already accepts them). ~15 lines, additive (existing wrapper
  keeps working).
- Verify `CuteDslFusedMoENvfp4Runner` per-call construction doesn't
  bust the autotune cache or add overhead.
- CUDA-graph capture/replay validation of `cute_dsl_fused_moe_nvfp4`
  under SGLang-style preallocation.

Captured benefits / risks / decision criteria. Status: NOT decided;
revisit only after the existing PR queue settles.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

…erged 2026-05-04

PR flashinfer-ai#3198 merged 2026-05-04 18:58 UTC as squash-merge commit `393e83ea`.
fi's `get_max_num_tiles` formula now matches TRT-LLM's compact closed-
form, eliminating the +1 tile over-allocation when (E - L) % T != 0.

Updates the line-11 final-state entry and the line-4369 PR queue
annotation in follow-up flashinfer-ai#12.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Updates the line-4370 PR queue annotation in follow-up flashinfer-ai#12 to reflect
that convergence-patch is now upstream as PR flashinfer-ai#3226 (initially Draft,
promoted to full PR same day, awaiting review).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

…05-06

PR flashinfer-ai#3226 merged 2026-05-06 12:54 UTC as squash-merge commit
`979644f1`. Drops 4 redundant Python-side `.fill_(-1)` / `.zero_()`
calls in `moe_sort` and aligns else-branch allocations with trt-llm's
`torch::empty(...)` thop pattern.

Updates the line-4369 PR queue annotation in follow-up flashinfer-ai#12.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

PR flashinfer-ai#3216 merged 2026-05-06 22:09 UTC as squash-commit `e6ac7cc2`.
Replaces the pre-computed-tuple bucket cap with a bare-callable form
that adapts to runtime input dim. Pairs with the prealloc-fix
(now rebased onto post-flashinfer-ai#3216 main as HEAD `c7a81fdb`, ready to PR).

Updates the line-15 final-state entry, line-51 perf-investigation-
closed paragraph, and line-4369 PR queue annotation in follow-up flashinfer-ai#12.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>