AniZpZ 8e03b641ba [1/n] apply wna16marlin kernel in moe weight only quantization (#7683) ...

Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
Co-authored-by: yych0745 <1398089567@qq.com>
Co-authored-by: HandH1998 <1335248067@qq.com>
Co-authored-by: 弋云 <yiyun.wyt@antgroup.com>
Co-authored-by: walker-ai <2398833647@qq.com>

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

..

__init__.py

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

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

allreduce.py

…

attention.py

…

elementwise.py

…

flash_attn.py

…

fused_moe.py

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

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

gemm.py

…

grammar.py

…

kvcacheio.py

…

marlin.py

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

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

moe.py

…

sampling.py

…

scalar_type.py

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

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

sparse_flash_attn.py

…

speculative.py

…

top_k.py

…

utils.py

…

version.py

…