Files
xc-llm-ascend/vllm_ascend/distributed/__init__.py
eeethenQ 44a8301424 [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>
2025-04-15 15:11:35 +08:00

7 lines
231 B
Python

from vllm.distributed.kv_transfer.kv_connector.factory import \
KVConnectorFactory
KVConnectorFactory.register_connector(
"AscendHcclConnector", "vllm_ascend.distributed.llmdatadist_connector",
"LLMDataDistConnector")