/en/tags/rust/Recent content in Rust on Mi&Bee BlogHugo -- gohugo.ioen蓝宝石的傻话Fri, 12 Jun 2026 00:00:00 +0000/en/posts/telemetry/ebpf-oom-advance/Fri, 12 Jun 2026 00:00:00 +0000/en/posts/telemetry/ebpf-oom-advance/<p>The first two articles covered eBPF fundamentals and OOM Killer event tracing. This article goes deeper: container-level OOM pinpointing, real-time memory allocation rate tracking, and implementing the same functionality with the Rust Aya framework.</p> <h2 id="container-level-oom-pinpointing">Container-Level OOM Pinpointing</h2> <p>In Kubernetes, &ldquo;a Pod OOM&rsquo;d&rdquo; is actually a vague statement. A Pod consists of multiple containers, each belonging to different cgroups. eBPF can drill through this layer and precisely identify which container and which process caused the OOM.</p>/en/posts/aihelper/yolo-rust-deployment/Fri, 29 May 2026 00:00:00 +0000/en/posts/aihelper/yolo-rust-deployment/<h2 id="chapter-9-complete-yolo-tutorial-with-rust">Chapter 9: Complete YOLO Tutorial with Rust</h2> <p>With its three core characteristics of memory safety, zero-cost abstractions, and extreme performance, Rust has become the ultimate choice for production-grade YOLO deployment. In edge computing and high-concurrency scenarios, Rust&rsquo;s performance advantages are particularly significant.</p> <h2 id="yolo-related-libraries-in-rust-ecosystem">YOLO-related Libraries in Rust Ecosystem</h2> <table> <thead> <tr> <th>Library Name</th> <th><a href="Crates.io">Crates.io</a></th> <th>Maintenance Status</th> <th>Use Cases</th> <th>Recommendation Index</th> </tr> </thead> <tbody> <tr> <td><strong>ort (onnxruntime-rs)</strong></td> <td>v2.0.0</td> <td>Super Active</td> <td>Official ONNX binding, full platform support</td> <td>⭐⭐⭐⭐⭐</td> </tr> <tr> <td><strong>ultralytics-inference</strong></td> <td>v0.0.11</td> <td>Official Maintenance</td> <td>Official Ultralytics Rust library</td> <td>⭐⭐⭐⭐⭐</td> </tr> <tr> <td><strong>tract</strong></td> <td>v0.21.0</td> <td>Active</td> <td>Pure Rust inference engine, no external dependencies</td> <td>⭐⭐⭐⭐</td> </tr> <tr> <td><strong>opencv-rust</strong></td> <td>v0.94.0</td> <td>Active</td> <td>OpenCV binding, DNN + image processing</td> <td>⭐⭐⭐⭐</td> </tr> <tr> <td><strong>tch-rs</strong></td> <td>v0.15.0</td> <td>Active</td> <td>LibTorch binding, PyTorch models</td> <td>⭐⭐⭐</td> </tr> <tr> <td><strong>candle</strong></td> <td>v0.6.0</td> <td>Super Active</td> <td>HuggingFace pure Rust ML framework</td> <td>⭐⭐⭐⭐</td> </tr> </tbody> </table> <p><strong>Core Features Comparison:</strong></p>