[Feature] Add PD separation feature (#432)

### What this PR does / why we need it?
Adapt Disaggregated Prefill feature onto Ascend device

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

no

### How was this patch tested?

The test usage has been provided alongwith the PR, in
examples/offline_disaggregated_prefill_npu.py
To run it, do this
```
export PROMPT_DEVICE_ID=0,1
export DECODE_DEVICE_ID=2,3
python examples/offline_disaggregated_prefill_npu.py
```

---------

Signed-off-by: ZihuiQian <qianzihui@huawei.com>
Co-authored-by: ZihuiQian <qianzihui@huawei.com>
This commit is contained in:
eeethenQ
2025-04-15 15:11:35 +08:00
committed by GitHub
parent c7f6584d75
commit 44a8301424
8 changed files with 634 additions and 8 deletions

View File

@@ -150,7 +150,7 @@ class NPUPlatform(Platform):
@classmethod
def get_device_communicator_cls(cls) -> str:
return "vllm_ascend.communicator.NPUCommunicator"
return "vllm_ascend.distributed.communicator.NPUCommunicator"
@classmethod
def is_pin_memory_available(cls):