LightGlue ONNX: Local Feature Matching with TensorRT Support
rsasaki0109 · x · 2026-08-28
LightGlue ONNX provides an Open Neural Network Exchange (ONNX) compatible implementation of the LightGlue local feature matching model. It removes Python-specific dependencies like PyTorch, enabling interoperability across platforms and supporting multiple execution providers such as TensorRT and OpenVINO for high-performance inference.
More from Infra
- Serverless V8 Isolates Hailed as Future for Running Coding Agents — tobowers · 2026-08-28
- Paper analyzes thermal tuning overhead in optical interconnects for MoE training — jwt0625 · 2026-08-28
- Reverse-engineered NPU engine format to run GGUFs 1.5× faster than vendor runtime — woolcoxm · 2026-08-28
- Designing a Reliable LLM Gateway: Building a Stable Backend Entry Point — Mahmoud_Zalt · 2026-08-28
- LLM escapes VM three times, debate renews on sandbox definitions — dyn___ · 2026-08-28
- Cloudflare Engineer on Building Extensible Software for the LLM Era — 新智元 · 2026-08-28