ViperEkura cb51a3587b perf: optimize fused FP8 GEMM kernel

2026-08-18 19:56:15 +08:00

..

backend

perf: precompute ragged Q tile scheduling

2026-08-16 23:32:46 +08:00

lib

refactor: move compiled kernel .so files into extension/lib

2026-07-31 15:36:32 +08:00

ops

perf: optimize fused FP8 GEMM kernel

2026-08-18 19:56:15 +08:00

__init__.py

refactor: separate extension ops and backends

2026-08-16 21:15:52 +08:00

fp8.py

refactor: separate extension ops and backends

2026-08-16 21:15:52 +08:00

loader.py

feat: add fp8 training via cublasLt dispatch

2026-08-14 00:39:49 +08:00