Xiaoyu Zhang 3de09aadbc Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00

..

generate_kernels.py

Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00

kernel_bf16_ku4.cuh

Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00

kernel_bf16_ku4b8.cuh

Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00

kernel_bf16_ku8b128.cuh

Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00

kernel_fp16_ku4.cuh

Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00

kernel_fp16_ku4b8.cuh

Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00

kernel_fp16_ku8b128.cuh

Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00

kernel_marlin.cuh

Support compile sgl-kernel on cuda 13.0 (#9721)

2025-08-28 10:18:03 -07:00

kernel.h

Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00

marlin_template.h

Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00

ops.cu

Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00