chen 29a313a402 [Optimization] Support FA2/FA3/FA4 with attn_mask_q (#6354) ...

* support FA4 sm100

* flash attn backend support mask

* flash attn backend run flashmask correct

* add test for flash_attn_backend and flash_attn_func

* check

* add test for fa4

* requirements.txt add fa4 whl

* check test on sm100

* fix CI conflict

* add enable_torch_proxy for flash_mask

* lazy import fa4

* check

* fix tests import

* check test_load_mpt import

2026-02-05 14:39:00 +08:00

..

test_embedding.py

[Optimization] Support FA2/FA3/FA4 with attn_mask_q (#6354)

2026-02-05 14:39:00 +08:00

test_Ernie4_5_reward_serving.py

[Bug fix] fix pooling models (#5358)

2025-12-04 11:06:30 +08:00

test_Qwen3-Embedding_serving.py

[Feature] Support prefill batch inference for pooling models. (#5436)

2025-12-09 16:21:00 +08:00