Yikun Jiang be58d5f3d8 Bump torch_npu version to dev20250308.3 (#276) ...

### What this PR does / why we need it?
Bump torch_npu version to dev20250308.3 to fix performance regression on
multi-stream case:
e04c580d07
.


### Does this PR introduce _any_ user-facing change?
NO

### How was this patch tested?
CI passed

Signed-off-by: Yikun Jiang <yikunkero@gmail.com>

2025-03-09 15:59:15 +08:00

..

developer_guide

Add Document Branch Policy (#217)

2025-03-03 09:07:39 +08:00

logos

[Doc] Add sphinx build for vllm-ascend (#55)

2025-02-13 18:44:17 +08:00

user_guide

[Core] Support pooling (#229)

2025-03-04 15:59:34 +08:00

conf.py

Recover vllm-ascend dev image (#209)

2025-03-03 09:08:41 +08:00

faqs.md

[Doc] Add initial FAQs (#247)

2025-03-06 10:42:42 +08:00

index.md

[Doc] Add initial FAQs (#247)

2025-03-06 10:42:42 +08:00

installation.md

Bump torch_npu version to dev20250308.3 (#276)

2025-03-09 15:59:15 +08:00

quick_start.md

[Docs] Fix vllm and vllm-ascend version (#107)

2025-02-20 11:05:35 +08:00

tutorials.md

[CI/Build] Bump torch_npu to dev20250307.3 (#265)

2025-03-07 20:34:07 +08:00