ViperEkura a59ae8f32e fix: use c10::optional for o_part_buf/ml_part_buf decode kernel params

2026-08-06 20:50:48 +08:00

..

kernels

fix: use c10::optional for o_part_buf/ml_part_buf decode kernel params

2026-08-06 20:50:48 +08:00

tests

refactor: unify paged and contiguous attention kernels via KVSource policy

2026-08-05 14:06:13 +08:00

__init__.py

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

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

CMakeLists.txt

build: migrate CUDA kernel build to CMake

2026-08-04 21:27:22 +08:00