周周周 ddb10ac509 [Inference, rename] remove padding_offsets from atten use batch_id_per_token (#2880) ...

* remove padding_offsets from atten

2025-07-17 18:41:31 +08:00

..

graph_optimization

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

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

guided_decoding

Sync v2.0 version of code to github repo

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

layers

[Inference, rename] remove padding_offsets from atten use batch_id_per_token (#2880)

2025-07-17 18:41:31 +08:00

models

Fix rollout_model init (#2881)

2025-07-16 22:36:21 -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

[Inference, rename] remove padding_offsets from atten use batch_id_per_token (#2880)

2025-07-17 18:41:31 +08:00

load_weight_utils.py

[Feature][MTP] Support cacheKV transfer in per_chunk mode (#2890)

2025-07-17 17:58:08 +08:00

model_loader.py

[vl]remove duplicated load logic (#2744)

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

pre_and_post_process.py

[Inference, rename] remove padding_offsets from atten use batch_id_per_token (#2880)

2025-07-17 18:41:31 +08:00