Peipei c4b976af1a [Model][VLM][Patch]Modify ascend affinity _merge_multimodal_embeddings (#3071) ...

### What this PR does / why we need it?

This PR aims to address the incompatibility of the `.masked_scatter_`
operation in the current `_merge_multimodal_embeddings` function on
Ascend. For now, it reverts to the previous version of the CPU
operation, which can be executed asynchronously on the device side to
enhance performance.

- vLLM version: v0.10.2
- vLLM main:
f225ea7dd9

---------

Signed-off-by: booker123456 <945658361@qq.com>

2025-09-24 10:25:28 +08:00

..

patch_common

[Model][VLM][Patch]Modify ascend affinity _merge_multimodal_embeddings (#3071)

2025-09-24 10:25:28 +08:00

patch_main

[Patch] format patch module to make it more clear (#601)

2025-04-22 14:13:00 +08:00

__init__.py

[Quickfix] update CachedRequestState as NewRequestData changed (#2367)

2025-08-15 07:35:27 +08:00