…fall

Co-authored-by: Cursor <cursoragent@cursor.com>
(cherry picked from commit 1d56f32)

…mized kernel

Co-authored-by: Cursor <cursoragent@cursor.com>
(cherry picked from commit 099f1c1)

Profile/cudagraph path resolved combine geometry via the op tuning table and
never forwarded --combine-block-num/--combine-warp-per-block, making config
sweeps no-ops. Pin the CLI geometry (when both are given) onto every FlyDSL
combine() call; default (unset) still falls back to the op tuning table.

(cherry picked from commit 265aed0)

(cherry picked from commit 6f81261)

(cherry picked from commit a193196)

… slim comments

…_uniform_i64; slim docstrings

…Vec/shuffle/filled, dedup fp8 pack, clean unused)

…ms + default_* fields)

…t switches

Refresh r1/pro/flash bf16 combine block_num/warp_per_block from the
full profiler+cudagraph sweep; add missing num_tokens buckets
(pro/flash 512/1024/2048, r1 8192).