baxingpiaochong 8786412f5c [Bugfix]KV pool rank 0 consumes more HBM (#6113) ...

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

before add_set_deivce
<img width="2354" height="674" alt="image"
src="https://github.com/user-attachments/assets/8b81ab5f-b9ba-4fd2-8546-8f36ac15d32b"
/>
after
<img width="1044" height="156" alt="image"
src="https://github.com/user-attachments/assets/996d845a-8abd-4aae-b894-4a9832b1f742"
/>

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.13.0
- vLLM main:
d68209402d

---------

Signed-off-by: baxingpiaochong <771405853@qq.com>

2026-01-23 19:47:33 +08:00

..

device_communicators

[Refactor]Refactor of vllm_ascend/distributed module (#5719)

2026-01-15 08:57:40 +08:00

kv_transfer

[Bugfix]KV pool rank 0 consumes more HBM (#6113)

2026-01-23 19:47:33 +08:00

__init__.py

[Refactor]Refactor of vllm_ascend/distributed module (#5719)

2026-01-15 08:57:40 +08:00

parallel_state.py

[Feature] Support DSA-CP for Hybrid scenario (#5702)

2026-01-22 10:12:09 +08:00

utils.py

[Feature] Support DSA-CP for Hybrid scenario (#5702)

2026-01-22 10:12:09 +08:00