AIPython★ 0
zorost/sparkduet
SparkDuet: on-demand model library
The project provides a single OpenAI‑compatible endpoint for running DeepSeek and Qwen models. It serves them via two vLLM lanes (TP=2) on an NVIDIA DGX Spark cluster and supports fine‑tuning with Unsloth QLoRA.
// KEY FEATURES
- Launch DeepSeek and Qwen via a single OpenAI‑compatible endpoint
- Two vLLM lanes (TP=2) provide low latency and high throughput
- On‑demand model library: load and unload models on request
- Supports fine‑tuning with Unsloth QLoRA on 2× DGX Spark
#coding-agents#deepseek#dgx-spark#fine-tuning#gb10#homelab#llama-swap#llm-inference#llm-serving#local-ai#local-llm#nvidia
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram