Gahow Wang a2de146fb6 Add Qwen3.6 MoE inference support

2026-07-13 20:24:41 +08:00

..

activation

Add Qwen3.6 MoE inference support

2026-07-13 20:24:41 +08:00

attention

Add Qwen3.6 MoE inference support

2026-07-13 20:24:41 +08:00

embedding

Add Qwen3.6 MoE inference support

2026-07-13 20:24:41 +08:00

gemm

speculative: batched-GEMV kernel for verify path (Phase 24 step 1)

2026-07-01 16:13:37 +08:00

moe

Add Qwen3.6 MoE inference support

2026-07-13 20:24:41 +08:00

normalization

kernels/cuda: paged-attention kernel, dispatch, pinned host memory

2026-05-28 19:58:36 +08:00

quantization

cuda: fix remaining int32-address and nondeterministic-reduction bugs

2026-07-01 15:13:07 +08:00

reduce

softmax: cap block size at 512 threads

2026-07-01 14:16:32 +08:00

test

phase 0+1: project scaffold + xserv-cuda crate

2026-05-21 18:40:22 +08:00

common.cuh

cuda: fix int32 overflow in MoE dense kernels; surface launch errors in release

2026-07-01 12:37:21 +08:00