3 Commits

Include renames

Author	SHA1	Message	Date
ViperEkura	15862d4b56	perf: fuse fp8 linear fwd and bwd into single kernel calls ... - fp8_linear_forward: cast + cublasLt GEMM + transpose + bias in one call - fp8_linear_backward: scale-free, dtype derived from input tensor - drops per-op Python dispatch (was ~6-8 launches per linear) and amax syncs - 1024x1024 linear: 6.8x slow -> 0.67x (36.7us vs 24.8us bf16) - small-model e2e still 1.71x slow; 15bt estimate ~0.78x (linear-heavy)	2026-08-14 01:24:37 +08:00
ViperEkura	c6a82a5029	refactor: align linear backward dtype with weight ... - cast gradients and inputs to weight.dtype instead of hardcoded bf16 - single code path covers bf16 and fp32 models, no branch needed - gradient dtype now matches the leaf parameter dtype exactly	2026-08-14 01:01:58 +08:00
ViperEkura	a5b238dd86	feat: add fp8 training via cublasLt dispatch ... - fp8_mm kernel (csrc): cublasLt fp8 e4m3 gemm, TN layout mapped zero-copy - custom::fp8_mm custom op: meta/cuda/cpu kernels + scale-corrected bf16 autograd - aten::linear and linear_backward dispatch on CUDA key, zero model changes - per-tensor scale or raw cast; single-GPU smoke loss matches bf16	2026-08-14 00:39:49 +08:00