R_REDDYX.XYZ
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
← Full catalog·Full index

// SIMILAR REPOSITORIES

🐍 CTI RAG★ 0🐍 ALEXANDRIA AUDIOBOOK★ 0🤖 SKILLS MANAGER★ 0🤖 MEDGECLAW★ 0🐍 SWE AF★ 0🤖 CLAUDE FORGE★ 0

← FULL CATALOG

zorost/sparkduet — SparkDuet: on-demand model library