biondizzle 452ba604fc restore tBgK to kh.count indexing (single-tile working), add TODO for multi-tile ...

CuTeDSL TMA copy API doesn't support dynamic GMEM tile indexing.
kh.count works for single tile. For multi-tile, need to either:
1. Map pipeline count to tile index (kh.count // 2 for interleaved K/V)
2. Separate K and V into non-interleaved TMA loops
3. Use gK/gV layouts that iterate naturally with pipeline count

This is the architectural blocker for multi-tile FMHA.

2026-05-22 15:54:03 +00:00

..

archive

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

e2e

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

integration

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

unit

Revert "debug: test 12w identity softmax with n=256 to verify multi-tile pipeline"

2026-05-22 10:25:48 +00:00

fmha_v3_stage_c_example1.py

restore tBgK to kh.count indexing (single-tile working), add TODO for multi-tile

2026-05-22 15:54:03 +00:00

native_stage_c_patch.py

more stuff

2026-05-22 08:57:38 +00:00

requirements.txt

test: add standalone layer 0 comparison test (no vLLM, no Docker)

2026-05-16 02:13:18 +00:00

run_test.sh

fix: use setup.py install for CUTLASS extension build

2026-05-16 02:21:17 +00:00