chen 7c1fd19f0f [OPs] MoE support wfp8afp8(channelwise) and improve per_token_quant_fp8 (#4238)

2025-09-24 16:39:51 +08:00

..

ops

[Optimize] Support WINT8 and group scale for Machete (#3905)

2025-09-15 12:01:34 +08:00

__init__.py

[BugFix]fix v1 loader moe bf16, and supoort dynamic_load_weight create quant param (#4229)

2025-09-24 14:12:05 +08:00

block_wise_fp8.py

[v1 loader]qwen Offline fp8 (#4036)

2025-09-15 13:44:11 +08:00

kv_cache.py

[BugFix]Fix load kv cache quant scale (#4077)

2025-09-12 17:44:03 +08:00

mix_quant.py

[v1 loader]qwen Offline fp8 (#4036)

2025-09-15 13:44:11 +08:00

quant_base.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

tensor_wise_fp8.py

[NewFeatures] support eplb (#3547)

2025-08-26 16:19:30 +08:00

w4a8.py

load hadamard_block_size from config (#3797)

2025-09-05 17:07:58 +08:00

w4afp8.py

load hadamard_block_size from config (#3797)

2025-09-05 17:07:58 +08:00

w8a8.py

fix w8a8.py (#3733)

2025-09-03 10:57:26 +08:00

weight_only.py

[Optimize] Machete using group scale default (#4121)

2025-09-18 13:51:11 +08:00

wfp8afp8.py

[OPs] MoE support wfp8afp8(channelwise) and improve per_token_quant_fp8 (#4238)

2025-09-24 16:39:51 +08:00

wint2.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00