YuanRisheng 88ea565aba [BugFix]Fix load kv cache quant scale (#4077) ...

* fix kv cache

* fix kv_cache

* fix kv cache

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

..

ops

[FIX]Fix Machete compile via ENABLE_MACHETE (#3727)

2025-08-30 17:50:17 +08:00

__init__.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

block_wise_fp8.py

MoE Default use triton's blockwise fp8 in TP Case (#3678)

2025-08-29 11:07:30 +08:00

kv_cache.py

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

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

mix_quant.py

cache feature (#3857)

2025-09-07 18:52:46 +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

[Feature] refactor metax_gpu attention and moe and remove some useless code (#3688)

2025-09-12 14:40:25 +08:00

wfp8afp8.py

[Feature] GLM-45-AIR Support Mix Quantization(Dense wfp8afp8 and wint8 triton_moe_backend) (#4051)

2025-09-11 20:08:09 +08:00

wint2.py

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

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