Open Issues Need Help
View All on GitHub AI/ML • Personal Assistants
vLLM PoC — Tek modelle OpenAI-compatible server ayağa kaldır about 2 months ago
AI Summary: This issue proposes a proof-of-concept (PoC) to set up an OpenAI-compatible server using vLLM on an NVIDIA GPU. The goal is to launch a selected LLM model (like Qwen2.5 or Llama) with a single command and verify its functionality and performance through basic client requests and latency checks.
Complexity:
2/5
good first issue priority:P0 area:llm vllm llm-backend
AI-powered voice assistant with browser automation, wake word detection, and LLM integration
Python