feat(npu): add bounded OpenVINO GenAI worker
This commit is contained in:
@@ -0,0 +1,17 @@
|
||||
[Unit]
|
||||
Description=OpenVINO GenAI NPU worker prototype
|
||||
After=network-online.target
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
WorkingDirectory=/home/will/lab/swarm/openvino-genai-npu-worker
|
||||
Environment=OV_GENAI_NPU_MODEL=/home/will/models/openvino-genai/Qwen2.5-1.5B-Instruct-int4-ov
|
||||
Environment=OV_GENAI_NPU_CACHE=/home/will/.cache/openvino/genai-npu/qwen2.5-1.5b-int4
|
||||
Environment=OV_GENAI_NPU_HOST=127.0.0.1
|
||||
Environment=OV_GENAI_NPU_PORT=18820
|
||||
ExecStart=/home/will/.venvs/npu/bin/python /home/will/lab/swarm/openvino-genai-npu-worker/worker.py --host 127.0.0.1 --port 18820
|
||||
Restart=on-failure
|
||||
RestartSec=5
|
||||
|
||||
[Install]
|
||||
WantedBy=default.target
|
||||
Reference in New Issue
Block a user