chen 0bcf924e10 [Optimization] Optimization for gather_logprob by 10GB (#5817) ...

* opt logprobs gather_logprob,reduce device memory usage by 10GB when token_num=8k

2025-12-30 15:33:34 +08:00

..

attention

make flash_mask attention pybind (#5783)

2025-12-26 14:31:35 +08:00

backends

[XPU] refactor moe ffn (#5501)

2025-12-18 14:14:05 +08:00

batch_invariant_ops

[Deterministic] Move paddle version batch invariant pkg to Fastdeploy (#4763)

2025-12-01 11:25:48 +08:00

moe

[Feature] support w4afp8 v1_loader and v0_loader(tp>1) (#5757)

2025-12-30 14:11:52 +08:00

pool

[Feature] support reward model (#5301)

2025-12-02 14:55:31 +08:00

quantization

[Feature] support w4afp8 v1_loader and v0_loader(tp>1) (#5757)

2025-12-30 14:11:52 +08:00

sample

[Optimization] Optimization for gather_logprob by 10GB (#5817)

2025-12-30 15:33:34 +08:00

__init__.py

[LLM] First commit the llm deployment code

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

activation.py

fix the get_act_fn,_load_st_projector (#4824)

2025-11-06 16:13:35 +08:00

embeddings.py

[Model] tp+ep support v1_loader (#5465)

2025-12-18 14:31:54 +08:00

linear.py

[Model] tp+ep support v1_loader (#5465)

2025-12-18 14:31:54 +08:00

lm_head.py

[Model] tp+ep support v1_loader (#5465)

2025-12-18 14:31:54 +08:00

mtp_linear.py

[Model] tp+ep support v1_loader (#5465)

2025-12-18 14:31:54 +08:00

normalization.py

[Model] tp+ep support v1_loader (#5465)

2025-12-18 14:31:54 +08:00

pooler.py

[Feature] support reward model (#5301)

2025-12-02 14:55:31 +08:00

rotary_embedding.py

[Models] Add Qwen3-VL Model Support (#5763)

2025-12-29 17:39:33 +08:00

utils.py

Remove CUDA ERROR 9 of inputs of get_padding_offset kernel (#5440)

2025-12-09 14:17:30 +08:00