Li Wang 3f9752f8ee [Bugfix]Lazy import vllm config (#462) ...

### What this PR does / why we need it?
Lazy import vllm config  to avoid circular imports

---------

Signed-off-by: wangli <wangli858794774@gmail.com>

2025-04-03 16:03:08 +08:00

..

attention

[Core] Make V1 work and enable V1 engine test (#389)

2025-03-28 19:34:23 +08:00

models

FastPatch: Optimized Patch Embedding for Qwen2VL (#345)

2025-03-26 14:28:20 +08:00

ops

[Feature] Implement EP-compatible fused_moe (#121)

2025-03-11 21:08:02 +08:00

quantization

[BugFix] Fix bugs when using ascend quantization (#275)

2025-03-12 11:33:21 +08:00

worker

[ModelRunner][V1] Optimize V1 attention mask (#442)

2025-04-02 10:33:53 +08:00

__init__.py

register qwen2_vl to rewrite qwen2_vl forwad (#241)

2025-03-07 15:41:47 +08:00

communicator.py

[Dist] Set device as rank (#202)

2025-03-03 09:23:13 +08:00

envs.py

[core] Support custom ascendc kernels in vllm-ascend (#233)

2025-04-03 14:52:34 +08:00

platform.py

[Bugfix]Lazy import vllm config (#462)

2025-04-03 16:03:08 +08:00

utils.py

support multistep decode (#299)

2025-03-11 19:20:06 +08:00