fems14 8b98d7a4e8 【main】【bugfix】Resolved memory deallocation failure in the pooling layer under re-computation workloads. (#6045) ...

### What this PR does / why we need it?
Resolved a double-free memory vulnerability in the pooling layer under
re-computation scenarios.
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

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

Signed-off-by: fems14 <1804143737@qq.com>

2026-01-20 22:56:04 +08:00

..

device_communicators

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

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

kv_transfer

【main】【bugfix】Resolved memory deallocation failure in the pooling layer under re-computation workloads. (#6045)

2026-01-20 22:56:04 +08:00

__init__.py

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

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

parallel_state.py

[refactor] Refactor the interface for shard weight and remove the flashcomm2 o_shared interface. (#5181)

2026-01-08 09:05:02 +08:00

utils.py

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

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