GitHub - Pogud/pogud.github.io: 🚀 Accelerate Qwen3-0.6B inference with MegaQwen, a custom CUDA megakernel achieving 531 tok/s on RTX 3090, 3.9x faster than existing frameworks.

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
odontoglossate		odontoglossate
index.md		index.md

About

🚀 Accelerate Qwen3-0.6B inference with MegaQwen, a custom CUDA megakernel achieving 531 tok/s on RTX 3090, 3.9x faster than existing frameworks.

github.com/Pogud/MegaQwen

No releases published