feat: refresh OpenVINO GenAI NPU worker prototype

This commit is contained in:
William Valentin
2026-06-04 12:13:44 -07:00
parent cb874f9743
commit b538a5a1f9
7 changed files with 253 additions and 36 deletions
@@ -7,6 +7,7 @@ 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