Article URL: https://github.com/me-farza/lightreason/tree/main
Comments URL: https://news.ycombinator.com/item?id=50487861
Points: 9
# Comments: 0
AI & ML
6-11X speedup running Qwen3.6 on my RTX 4090, full repo.
Hacker News0 views
Source：https://github.com/me-farza/lightreason/tree/main
PreviousRun Native DLA Inference in Python on NVIDIA Jetson AGX Orin Using cuDLANextIt Takes 16 Clicks for a Student to Open a PowerPoint on an iPad
Related posts
Export-banned Nvidia chips are behind China’s most powerful AI models — uh oh, Jensen!
0TechCrunch
OpenAI disbands its robotics team as its general models start running robots
0Hacker News
Run Native DLA Inference in Python on NVIDIA Jetson AGX Orin Using cuDLA
0NVIDIA Developer Blog
I scanned 6 popular repos the way a coding agent reads them. LangChain's lockfiles outweigh its code.
0dev.to AI
Nano Banana 3.0 Writes the Headline and Keeps the Face Across Scenes
0dev.to AI
How OpenAI Made Voice AI Feel Like a Real Conversation: 8 Engineering Changes
0dev.to AI