exo-explore · Inference Engine
Exo
Since Week 39 2025: shipped v1.0 with day-0 RDMA over Thunderbolt 5 on M-series Macs, cutting inter-device latency from 300 to 3 microseconds and enabling up to 3.2x tensor-parallel speedup across 4 devices. Added a macOS app/dashboard plus OpenAI/Claude/Ollama-compatible APIs. 46,589 stars.
Open the source ↗Similar Developer Tools releases
- DeepInfer
DeepSeek · Inference Engine · Week 44, 2026
- Toward Recursive Self-Improvement
Z.ai · Self-Built Inference Stack · Week 39, 2026
- A Hardware-Level Tour of LLM Inference
Dr Ashish Bamania · LLM Inference Internals · Week 36, 2026
- Kie.ai
Kie.ai · AI Infrastructure · Week 31, 2026
- WaveSpeedAI
WaveSpeedAI · Inference Engine · Week 31, 2026
- QwenCloud Token Plan
Alibaba / QwenCloud · AI Infrastructure · Week 30, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.