OpenVINO
PulseAugur coverage of OpenVINO — every cluster mentioning OpenVINO across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
llama.cpp releases bring performance boosts and broader platform support
The llama.cpp project has released several updates, including performance optimizations for the SSM_CONV operation on Intel Arc Pro B70 hardware and improvements to NORM and RMS_NORM calculations on Apple Silicon. These…
-
llama.cpp releases multiple updates with cross-platform optimizations
The llama.cpp project has released several updates, including versions b10106, b10105, b10108, b10099, b10098, b10094, b10093, b10092, b10091, and b10103. These releases introduce various improvements and fixes across d…
-
Intel GPU challenges NVIDIA in AI inference on cost and performance
Intel's Arc Pro B70 GPU is reportedly outperforming NVIDIA's RTX 5090D in DeepSeek R1 AI inference tasks, while costing significantly less. This development challenges the dominance of NVIDIA's CUDA ecosystem, suggestin…
-
Benchmarking edge inference frameworks for industrial machine vision · 2 sources tracked
A new research paper benchmarks the performance of four popular frameworks—PyTorch, ONNX Runtime, OpenVINO, and TensorRT—for deep learning inference on edge devices in industrial machine vision. The study found that Ope…
-
Laptop iGPU VRAM Ceiling Limits Local LLM Performance
Running large language models (LLMs) and AI tasks locally on laptops is primarily constrained by the integrated GPU's (iGPU) Video RAM (VRAM) rather than the CPU. Laptops with 16GB of system RAM typically allocate about…
-
llama.cpp releases multiple updates with performance and bug fixes
The llama.cpp project has released several updates, including versions b9975, b9974, b9973, b9972, b9971, b9970, b9969, b9968, b9966, and b9965. These releases introduce various improvements and bug fixes across multipl…
-
llama.cpp Releases Enhance Performance and Add New Features
The llama.cpp project has released several updates, including b9608, which features an update to cpp-httplib and provides pre-compiled binaries for various platforms like macOS, Linux, Android, and Windows. Release b960…
-
New method improves causal discovery in Large Behavioural Models
Researchers have developed a method to improve the accuracy of causal discovery in Large Behavioural Models (LBMs) by addressing issues with embedding proximity. Standard biomedical language models incorrectly associate…
-
New method slashes LLM quantization bit-width with spectral rotations
Researchers have developed a novel method called BBT-spectral for quantizing large language models (LLMs) to extremely low bit-widths, specifically W2A16 (2-bit weights, 16-bit activations). This technique utilizes infl…
-
Developer runs LLMs on $50 AMD RX 580 GPU using Vulkan
A developer demonstrated running large language models and image generation software on an older AMD RX 580 GPU with 8GB of VRAM, a feat previously thought impossible for such hardware. By leveraging the Vulkan backend …
-
llama.cpp releases add Vulkan, optimize matrix math, and improve server logging
The llama.cpp project has released several updates, including version b9580 which adds Vulkan support for matrix-matrix multiplication and Flash Attention, along with optimizations for FP16 dot2 extensions. Other recent…
-
Intel NCS2 shows significant fault vulnerability under EM injection
Researchers have characterized the fault response of the Intel Neural Compute Stick 2 (NCS2) when subjected to electromagnetic fault injection. Their experiments revealed four distinct outcome classes, including silent …
-
Hugging Face releases open multilingual embedding models with 32K context
Hugging Face has released Granite Embedding Multilingual R2, a suite of open-source multilingual embedding models. The release includes a 97M-parameter compact model that leads in retrieval quality among open models und…
-
Hugging Face blog posts cover Intel CPU VLM, MiniMax M2 agents, and Gradio custom frontends
This cluster highlights three distinct technical blog posts from Hugging Face, shared via Mastodon. The first post details how to run Vision-Language Models (VLMs) on Intel CPUs using OpenVINO. The second explores agent…
-
Hugging Face and Intel collaborate on Gaudi accelerators for efficient AI
Hugging Face has released new resources and guides detailing how to leverage Intel's Gaudi 2 AI accelerators for efficient AI model training and deployment. These collaborations focus on optimizing performance for tasks…