Peng Zhang 5aa1ebd242 [2/n]decouple quantization implementation from vLLM dependency (#8112) ...

Co-authored-by: walker-ai <yiyun.wyt@antgroup.com>
Co-authored-by: leoneo <1320612015@qq.com>

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

..

generate_kernels.py

[1/n] apply wna16marlin kernel in moe weight only quantization (#7683)

2025-07-01 23:21:25 -07:00

kernel_bf16_ku4.cu

[1/n] apply wna16marlin kernel in moe weight only quantization (#7683)

2025-07-01 23:21:25 -07:00

kernel_bf16_ku4b8.cu

[1/n] apply wna16marlin kernel in moe weight only quantization (#7683)

2025-07-01 23:21:25 -07:00

kernel_bf16_ku8b128.cu

[1/n] apply wna16marlin kernel in moe weight only quantization (#7683)

2025-07-01 23:21:25 -07:00

kernel_fp16_ku4.cu

[1/n] apply wna16marlin kernel in moe weight only quantization (#7683)

2025-07-01 23:21:25 -07:00

kernel_fp16_ku4b8.cu

[1/n] apply wna16marlin kernel in moe weight only quantization (#7683)

2025-07-01 23:21:25 -07:00

kernel_fp16_ku8b128.cu

[1/n] apply wna16marlin kernel in moe weight only quantization (#7683)

2025-07-01 23:21:25 -07:00

kernel.h

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

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

marlin_template.h

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

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

ops.cu

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

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