Files
xc-llm-ascend/vllm_ascend
Li Wang 58adf7c8ac [Bugfix] Correctly handle the output shape in multimodal attention (#5443)
### What this PR does / why we need it?
Fix https://github.com/vllm-project/vllm-ascend/issues/5297, for
`AscendMMEncoderAttention` forward, we should keep the output shape
consistence with the input

- vLLM version: release/v0.13.0
- vLLM main:
81786c8774

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
2025-12-27 18:42:46 +08:00
..
2025-12-20 17:03:25 +08:00
2025-12-11 18:45:43 +08:00
2025-12-25 09:17:06 +08:00
2025-12-02 17:35:47 +08:00
2025-12-26 14:07:37 +08:00
2025-12-26 14:07:37 +08:00