Ryan fefbd65cf8 [SOT] Remove BreakGraph with paddle.maximum (#2731) ...

* rm if with clip

* clip -> maximum

* int64 -> int32

2025-07-08 11:44:25 +08:00

..

graph_optimization

Sync v2.0 version of code to github repo

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

guided_decoding

Sync v2.0 version of code to github repo

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

layers

[Bug fix] fix complie bug when sm < 89 (#2738)

2025-07-08 11:24:52 +08:00

models

[SOT] Remove BreakGraph with paddle.maximum (#2731)

2025-07-08 11:44:25 +08:00

ops

Adapt for iluvatar gpu (#2684)

2025-07-07 16:53:14 +08:00

__init__.py

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

load_weight_utils.py

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

model_loader.py

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

pre_and_post_process.py

Adapt for iluvatar gpu (#2684)

2025-07-07 16:53:14 +08:00