yzwu ac013803f3 [Iluvatar] Support V1_KVCACHE_SCHEDULER and paddleocr-vl rope mode (#5555)

2025-12-18 02:14:25 -08:00

..

ops

FA3 support qwen3 (#5441)

2025-12-09 16:16:16 +08:00

__init__.py

[Feature] support flash_mask_attention backend (#5134)

2025-11-28 10:12:16 +08:00

append_attn_backend.py

[Graph Optimization][CI] Add ERNIE45T 21B sot test (#5538)

2025-12-13 00:43:15 +08:00

attention_selecter.py

…

attention.py

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

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

base_attention_backend.py

…

block_multihead_attn_backend.py

[KVCache] support unified cache backend (#4903)

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

flash_attn_backend.py

FA3 support qwen3 (#5441)

2025-12-09 16:16:16 +08:00

flash_mask_attn_backend.py

FA3 support qwen3 (#5441)

2025-12-09 16:16:16 +08:00

iluvatar_attn_backend.py

[Iluvatar] Support V1_KVCACHE_SCHEDULER and paddleocr-vl rope mode (#5555)

2025-12-18 02:14:25 -08:00

mla_attention_backend.py

[PD Disaggregation] Support PD deployment of DeepSeekv3. (#5251)

2025-12-02 14:11:50 +08:00

moba_attention_backend.py

[KVCache] support unified cache backend (#4903)

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

native_paddle_backend.py

…

utils.py

[PD Disaggregation][XPU] Add XPU support for PD disaggregation (#5113)

2025-11-21 14:09:01 +08:00

xpu_attn_backend.py

[XPU] refactor of block_attn param 'pos_emb_type' (#5511)

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