Jinzhen Lin e73b7dfd69 [Bugfix] fix an illegal memory access was encountered of marlin kernel + act_order (#18245)

2025-05-16 16:02:44 -07:00

..

.gitignore

[Kernel] some optimizations for dense marlin and moe marlin (#16850)

2025-05-05 09:39:30 -07:00

awq_marlin_repack.cu

Fix CUDA kernel index data type in vllm/csrc/quantization/gptq_marlin/awq_marlin_repack.cu +10 (#15160)

2025-03-25 15:36:45 +08:00

dequant.h

[Kernel] fp4 marlin kernel (#17687)

2025-05-10 19:58:49 -07:00

generate_kernels.py

[Kernel] fp4 marlin kernel (#17687)

2025-05-10 19:58:49 -07:00

gptq_marlin_repack.cu

Fix CUDA kernel index data type in vllm/csrc/quantization/gptq_marlin/awq_marlin_repack.cu +10 (#15160)

2025-03-25 15:36:45 +08:00

gptq_marlin.cu

[Kernel] fp4 marlin kernel (#17687)

2025-05-10 19:58:49 -07:00

kernel.h

[Kernel] fp4 marlin kernel (#17687)

2025-05-10 19:58:49 -07:00

marlin_dtypes.cuh

[Kernel] moe wna16 marlin kernel (#14447)

2025-04-14 20:05:22 -07:00

marlin_template.h

[Bugfix] fix an illegal memory access was encountered of marlin kernel + act_order (#18245)

2025-05-16 16:02:44 -07:00

marlin.cuh

[Kernel] moe wna16 marlin kernel (#14447)

2025-04-14 20:05:22 -07:00