KernelBench hard · RTX PRO 6000

W4A16 GEMM Kimi K3 (256k)

manually audited: clean

Genuine fused W4A16 (int4-weight, bf16-activation) GEMM with two real paths: an M==1 CUDA GEMV (load_inline, sm_90a) using byte_perm bf16 magic-number (0x4300) nibble dequant against live per-128-group scales/zeros, with split-K float partials and a self-resetting atomic-counter combine; and a Triton fused-dequant tl.dot kernel for M>1. The only cache is _prep's _so (interleaved scales / zeros+128 layout for the GEMV), keyed on weight buffer _version/data_ptr/device and invalidated by a load_state_dict post hook — the legitimate weight-repack pattern, not output caching. Output tensors are freshly allocated (torch.empty) every forward. 0.1233 geomean peak fraction from real per-shape timings.

20260715_204121_kinetic-claude_kinetic-0715_07_w4a16_gemm