ViperEkura 9f48cb8928 refactor: streamline Q block mapping ...

- bypass shared mapping for contiguous attention
- centralize paged Q tile broadcast in KV policy helpers

2026-08-10 08:40:18 +08:00

..

kernels

refactor: streamline Q block mapping

2026-08-10 08:40:18 +08:00

tests

perf: flatten paged prefill tile dispatch

2026-08-09 23:12:53 +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