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

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

..

awq_marlin_repack.cu

…

dequant.h

Add new moe wna16 marlin gemm (#14122)

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

gptq_marlin_repack.cu

…

gptq_marlin.cu

…

kernel.h

…

marlin_dtypes.cuh

…

marlin_template.h

…

marlin.cuh

[2/n]decouple quantization implementation from vLLM dependency (#8112)

2025-08-14 03:19:03 -07:00