Ryan b0f525955c [SOT] Remove breakgraph in post processing && fix datatype (#2780)

2025-07-10 11:26:00 +08:00

..

ops

[SOT] Remove breakgraph in post processing && fix datatype (#2780)

2025-07-10 11:26:00 +08:00

__init__.py

dcu adapter ernie45t (#2756)

2025-07-09 18:56:27 +08:00

append_attn_backend.py

fix ep prefill (#2762)

2025-07-09 14:03:05 +08:00

attention_selecter.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

attention.py

Adapt for iluvatar gpu (#2684)

2025-07-07 16:53:14 +08:00

base_attention_backend.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

block_multihead_attn_backend.py

dcu adapter ernie45t (#2756)

2025-07-09 18:56:27 +08:00

flash_attn_backend.py

fix ep prefill (#2762)

2025-07-09 14:03:05 +08:00

iluvatar_attn_backend.py

Adapt for iluvatar gpu (#2684)

2025-07-07 16:53:14 +08:00

mla_attention_backend.py

dcu adapter ernie45t (#2756)

2025-07-09 18:56:27 +08:00

native_paddle_backend.py

Sync v2.0 version of code to github repo

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

utils.py

fix ep prefill (#2762)

2025-07-09 14:03:05 +08:00

xpu_attn_backend.py

Revert "[Bug fix] fix attention rank init (#2743)" (#2761)

2025-07-09 10:38:12 +08:00