SuperNova 805f29a06c [Feature] refactor metax_gpu attention and moe and remove some useless code (#3688) ...

Co-authored-by: yongqiangma <xing.wo@163.com>

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

..

graph_optimization

[Executor] Adjust signal sending order in RL training (#3773)

2025-09-10 13:24:20 +08:00

guided_decoding

[Feature] mm and thinking model support structred output (#2749)

2025-09-02 16:21:09 +08:00

layers

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

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

model_loader

cache feature (#3857)

2025-09-07 18:52:46 +08:00

models

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

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

ops

fix typos (#3840)

2025-09-12 11:04:38 +08:00

__init__.py

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

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

forward_meta.py

【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886)

2025-09-11 10:46:09 +08:00

load_weight_utils.py

[docs] Update environment variables documentation (#3957)

2025-09-10 21:17:06 -07:00

pre_and_post_process.py

support mtp in v1_scheduler mode (#3695)

2025-09-04 17:39:59 +08:00

utils.py

cache feature (#3857)

2025-09-07 18:52:46 +08:00