ViperEkura 1f0be382ad refactor: extract load_q_mma_frags template, unify comment style ...

- Add load_q_mma_frags<KD>() shared template in attn_mma_utils.cuh
- Replace ~15 duplicated Q-load lines in 3 MMA kernels
- Unify section header comment style to // ---- Section ----
- Remove duplicate separator line in attn_mma_utils.cuh

2026-07-15 19:07:18 +08:00

..

kernels

refactor: extract load_q_mma_frags template, unify comment style

2026-07-15 19:07:18 +08:00

tests

fix: uninitialized strides in decode test and wrong stride helper in paged test

2026-07-14 23:58:30 +08:00

__init__.py

feat: add optional CUDA kernel system (csrc/) + fused GQA decode attention

2026-07-06 12:09:58 +08:00

build.py

chore: bump version to 1.3.9

2026-07-12 21:04:20 +08:00