biondizzle 07817ae82e FIX: use unsliced tBgK with (None, kt, None, 0) for proper GMEM tile indexing ...

The pre-slice (None,0,None,0) hardcoded GMEM iteration to tile 0.
Instead, keep the original tBgK and index with (None, kt, None, 0)
inside the TMA loop, where kt selects the correct GMEM tile.
This preserves 2D rank matching with the SMEM tensor.

2026-05-22 15:52:56 +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

FIX: use unsliced tBgK with (None, kt, None, 0) for proper GMEM tile indexing

2026-05-22 15:52:56 +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