ViperEkura f9efb705b8 perf: output fp8 gemm in bf16 instead of fp32 ...

- cublasLt C layout and buffer switched to CUDA_R_16BF, halving output bandwidth
- downstream ops (RMSNorm etc.) keep matching bf16 dtype, fused kernels stay
- numeric error unchanged (0.19% vs fp32 ref on quantized inputs)

2026-08-14 01:08:26 +08:00

..

kernels

perf: output fp8 gemm in bf16 instead of fp32

2026-08-14 01:08:26 +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

feat: add fp8 training via cublasLt dispatch

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