Jade Zheng e04a5e3dd3 [Bugfix] Fix race condition in d2h transfer (#3372) ...

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

Using non-blocking operations for device-to-host transfers can lead to
data corruption in later steps. The CPU tensor is accessed right after
the transfer is triggered, but the transfer might not be complete yet.
As a result, the data could be wrong. This problem was seen in the A3
environment during `profile_run`.

### How was this patch tested?
CI pass.

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>

2025-10-20 18:24:21 +08:00

..

__init__.py

[3/N][refactor] refactoer quantization (#2504)

2025-08-27 10:45:50 +08:00

torchair_w4a8_dynamic.py

[BugFix]Support redundant experts in EPLB (#3473)

2025-10-18 00:09:16 +08:00

torchair_w8a8_dynamic.py

[Bugfix] Fix race condition in d2h transfer (#3372)

2025-10-20 18:24:21 +08:00