Ryan 49cea8fb1c [SOT][Cudagraph] Remove BreakGraph of #3302 && update CustomOp (#3694) ...

* rm inplace info && to(gpu)

* update append_attention

* unpin paddle version

* add full_cuda_graph=False

* add blank line

---------

Co-authored-by: SigureMo <sigure.qaq@gmail.com>

2025-10-17 10:57:55 +08:00

..

ops

[SOT][Cudagraph] Remove BreakGraph of #3302 && update CustomOp (#3694)

2025-10-17 10:57:55 +08:00

__init__.py

【FIX】Change the name of sparse attn from moba to plas (#4006) (#4076)

2025-09-23 10:26:40 +08:00

append_attn_backend.py

[SOT][Cudagraph] Remove BreakGraph of #3302 && update CustomOp (#3694)

2025-10-17 10:57:55 +08:00

attention_selecter.py

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

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

attention.py

【FIX】Change the name of sparse attn from moba to plas (#4006) (#4076)

2025-09-23 10:26:40 +08:00

base_attention_backend.py

[MetaxGPU] Support FastDeploy on metax gpu (#3241)

2025-08-13 11:11:54 +08:00

block_multihead_attn_backend.py

[FDConfig]Remove max_model_len in FDConfig (#4350)

2025-10-11 14:04:17 +08:00

flash_attn_backend.py

[Optimization] Fuse get_max_len and get_kv_max_len (#4369)

2025-10-13 20:35:00 +08:00

iluvatar_attn_backend.py

[FDConfig]Remove total_block_num/dtype/block_size/enc_dec_block_num in ParallelConfig (#4400)

2025-10-16 20:00:37 +08:00

mla_attention_backend.py

[Optimization] Fuse get_max_len and get_kv_max_len (#4369)

2025-10-13 20:35:00 +08:00

moba_attention_backend.py

[FDConfig]Remove total_block_num/dtype/block_size/enc_dec_block_num in ParallelConfig (#4400)

2025-10-16 20:00:37 +08:00

native_paddle_backend.py

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

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

utils.py

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

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

xpu_attn_backend.py

[XPU] fix VL multi-batch accuracy issue (#4394)

2025-10-15 17:27:43 +08:00