ming1753 69be77c8c0 [Feature] support prompt repetition_penalty (#2954) ...

* [Feature] support prompt repetition_penalty (#2806)

* [Bug Fix] fix bug of prompt penalty (#2888)

2025-07-22 19:42:33 +08:00

..

graph_optimization

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

guided_decoding

【Sync develop】support vl model name_mapping and ori_vocab_size (#2915)

2025-07-20 23:14:15 -07:00

layers

[Feature] support prompt repetition_penalty (#2954)

2025-07-22 19:42:33 +08:00

models

【Sync develop】support vl model name_mapping and ori_vocab_size (#2915)

2025-07-20 23:14:15 -07:00

ops

refactor rl get_name_mappings_to_training (#2847)

2025-07-15 07:31:42 -07:00

__init__.py

[LLM] First commit the llm deployment code

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

forward_meta.py

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

load_weight_utils.py

[Fix] Fix mm ep weight init. (#2855)

2025-07-16 12:02:39 +08:00

model_loader.py

[vl]remove duplicated load logic (#2744)

2025-07-13 07:36:26 +08:00

pre_and_post_process.py

Merge vl execution path into normal execution path (#2829)

2025-07-15 22:20:03 +08:00