pub fn k64_kernel(gpu: &dyn GpuBackend) -> Result<KernelHandle>Expand description
2026-09-25: The k64 deep-K tile GEMM. Prefers w4a16_gemm_t_k64_p3; takes
w4a16_gemm_t_k64 when METRALE_NO_K64_PIPELINE3 is set to any value
(0 included) or the target lacks _p3, and errors when that is missing too.