Zero Rains ce1f353c70 Move create_parameters to __init__ in FuseMOE for CultassBackend and TritonBackend (#3148) ...

* w4a8 bug

* fix w4a8 bug

* remove code

* modify the triton backend

* fix ep

* fix the bug with tensor_wise_fp8 in triton backend

* fix the RL

* fix bug by merge

* fix the bug in w4a8

* fix the tensor_wise_fp8 bug

* fix RL

2025-08-08 15:55:47 +08:00

..

ops

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

2025-07-19 23:19:27 +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

[bugfix]fix blockwisefp8 and all_reduce (#3243)

2025-08-06 23:54:33 +08:00

kv_cache.py

support c4 attn && fix cache

2025-07-24 12:00:52 +08:00

mix_quant.py

fix is_permuted (#3098)

2025-07-31 19:58:05 +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

Move create_parameters to __init__ in FuseMOE for CultassBackend and TritonBackend (#3148)

2025-08-08 15:55:47 +08:00

w4a8.py

fix is_permuted (#3098)

2025-07-31 19:58:05 +08:00

w4afp8.py

qwen3_moe (#3084)

2025-08-06 14:45:27 +08:00

w8a8.py

qwen3_moe (#3084)

2025-08-06 14:45:27 +08:00

weight_only.py

qwen3_moe (#3084)

2025-08-06 14:45:27 +08:00

wfp8afp8.py

qwen3_moe (#3084)

2025-08-06 14:45:27 +08:00

wint2.py

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

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