ViperEkura 7580d80d45 perf: accelerate FP8 backward with fused fast kernel ...

- route dX/dW through the fused 128x64 fast kernel via contiguous transposes
- drop the legacy 64x64 kernel, cutting dX 1.55->0.38 ms and dW 1.28->0.26 ms
- sync all threads after cp.async.wait_group to fix sporadic NaN in large GEMMs
- add fp8_mm_prequant_fp8 custom op for FP8-in/FP8-out GEMM

2026-08-18 23:46:43 +08:00

..

__init__.py

refactor: separate extension ops and backends

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

attention.py

perf: precompute ragged Q tile scheduling

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

fp8.py

perf: accelerate FP8 backward with fused fast kernel

2026-08-18 23:46:43 +08:00

rotary.py

refactor: separate extension ops and backends

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