ltd0924 5bf48de999 [KVCache] support unified cache backend (#4903) ...

* [Feature] support unified cache backend

* fix

* fix

* fix

* fix

* Update metax_model_runner.py

* fix

* update

* Update test_moba_attention_backend.py

---------

Co-authored-by: ltd0924 <luotingdan@baidu.com>

2025-11-12 14:54:52 +08:00

..

ops

Support GPT-OSS-BF16 (#4240)

2025-10-20 14:44:58 +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

[KVCache] support unified cache backend (#4903)

2025-11-12 14:54:52 +08:00

attention_selecter.py

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

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

attention.py

fix Cfp8 for RL load (#4144)

2025-11-03 17:51:51 +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

[KVCache] support unified cache backend (#4903)

2025-11-12 14:54:52 +08:00

flash_attn_backend.py

[KVCache] support unified cache backend (#4903)

2025-11-12 14:54:52 +08:00

iluvatar_attn_backend.py

[KVCache] support unified cache backend (#4903)

2025-11-12 14:54:52 +08:00

mla_attention_backend.py

[KVCache] support unified cache backend (#4903)

2025-11-12 14:54:52 +08:00

moba_attention_backend.py

[KVCache] support unified cache backend (#4903)

2025-11-12 14:54:52 +08:00

native_paddle_backend.py

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

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

utils.py

supports pd partn (#4615)

2025-11-04 16:36:35 +08:00

xpu_attn_backend.py

[KVCache] support unified cache backend (#4903)

2025-11-12 14:54:52 +08:00