Microsoft · Inference Engine
BitNet
Microsoft's inference framework for 1-bit (ternary) LLMs reports 2.37x to 6.17x speedups on x86 with 71.9-82.2% less energy, and 1.37x to 5.07x on ARM. July added VibeASR.cpp for multilingual speech recognition under BitNet quantisation plus 0.6B and 270M embedding models. MIT, 40.1k stars - and still no tagged GitHub release.
Open the source ↗Similar Developer Tools releases
- DeepInfer
DeepSeek · Inference Engine · Week 44, 2026
- Free Claude Code
Ali Shahryar (Alishahryar1) · Coding Agent Proxy · Week 44, 2026
- Needle 3
Cactus Compute · Tiny Device Model · Week 39, 2026
- Toward Recursive Self-Improvement
Z.ai · Self-Built Inference Stack · Week 39, 2026
- edge0
Edge0-AI · Streaming MoE Inference · Week 37, 2026
- ComfyUI-VDN-H3
Saganaki22 · VDN ComfyUI Node · Week 36, 2026
More from Microsoft
- Skill Recorder
Microsoft · Prompt Engineering · Week 33, 2026
- Mage-Flow
Microsoft · Text-to-Image · Week 30, 2026
- Microsoft Discovery (GA)
Microsoft · Agent Framework · Week 23, 2026
- Majorana 2
Microsoft · Research Paper · Week 23, 2026
- AI Engineering Coach
Microsoft · Prompt Engineering · Week 21, 2026
- TRELLIS 2
Microsoft · 3D Generation · Week 14, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.