Gahow Wang ce9d22ffc2 wip: T10 batched forward (validation)

2026-06-16 00:19:26 +08:00

..

elementwise.cu

tensor: add scale elementwise CUDA kernel + FFI

2026-06-15 15:13:06 +08:00

gemm.cu

gemm: tiled F32 forward + transpose + backward (dA/dB)

2026-06-15 15:26:51 +08:00

model.cu

ops: embedding/reshape/transpose/split-merge-heads fwd+bwd

2026-06-15 16:05:09 +08:00

nn.cu

wip: T10 batched forward (validation)

2026-06-16 00:19:26 +08:00

optim.cu

perf: GPU AdamW + grad-norm

2026-06-15 16:53:09 +08:00