Varun Rajput·1d agoWhy May a Model Get Slower on a Bigger Machine?When two libraries both assume they own every CPU core, adding cores can make things slower. Here’s why, and how to spot it.
Dhiraj Patra·4d agoHow to Convert Tensoflow/Keras Model to the ONNX FormatTo convert a TensorFlow/Keras model to the ONNX format, the industry-standard tool is tf2onnx.
Carlo C.·Oct 27Piper TTS on My Vulkan EP: 11× Faster Than CPU, 27% Smaller with INT8I write an open-source Rust engine, onnx-vulkan-rs, that runs ONNX models on Vulkan, the compute and graphics API that NVIDIA, AMD and…
Craig Walls·Oct 26Spring AI Recipe: Speeding Up RAG with Faster EmbeddingsIs your RAG application stuck in the slow lane? The embedding model might be the bottleneck. In this recipe, we’ll put five embedding…
Carlo C.·Oct 15Segment Anything 3 Without CUDA: a 7.9 MB Engine and 1 GB of int8 WeightsI write an open-source Rust engine, onnx-vulkan-rs, that runs ONNX models on Vulkan and targets any GPU with a Vulkan driver (so far tested…A response icon1A response icon1
olesha-ai·Oct 14I shipped an engine for your own UI: three DLLs, CPU, no CUDA required.I spent a long time building fruit inspection in “Fruit Inspector” — camera, line, control zone, classification. Not everyone wants my exe…
Dreamwalker(박제창)·Oct 12[Part 4/4] Building a Serverless On-Device Flutter Bird Field Guide App: LiteRT & WebGPU…Subtitle: Running a trimodal bird retrieval engine completely serverless on smartphones (Android/iOS LiteRT .tflite) and browsers (WebGPU…
InStackademicbyTsvetan Tsvetkov·Oct 12YOLOv26: Java Object Detection made easy with ONNXI’ve followed the YOLO models for quite some time now, and hearing that newer models remove the need for NMS (Non-Maximum Suppression) is…
Nikhil Ranjan·Oct 11Serve a PyTorch model over HTTP/S with Downshift-ServerServe a model with one command. Downshift-Server checks ONNX numbers before the first request.A response icon1A response icon1
Zouhour Bellamine·Oct 2From Notebook to Production: MLOps Foundations — Session 01A technical deep dive into MLOps maturity, production-grade Python, FastAPI, ONNX, Docker, testing, and observability.
![[Part 4/4] Building a Serverless On-Device Flutter Bird Field Guide App: LiteRT & WebGPU…](https://miro.medium.com/v2/resize:fill:160:106/1*-_I1ixeYU7Oms1WaVIUubA.png)
![[Part 4/4] Building a Serverless On-Device Flutter Bird Field Guide App: LiteRT & WebGPU…](https://miro.medium.com/v2/resize:fill:320:214/1*-_I1ixeYU7Oms1WaVIUubA.png)
