Auto Added by WPeMatico
Buoyant, the company behind Linkerd, has released Kinference, an open source project for building inference platforms on Kubernetes. Kinference is an inference control plane for Kubernetes and vLLM. It sits in front of a fleet of vLLM workers and decides where each request goes. It applies routing policies, token rate limits, KV-cache-aware load balancing and
Discovering new molecules for specific uses is a major driver of progress in a wide variety of industries, whether it’s pharmaceutical companies looking for new drugs, or electronics or energy companies seeking new materials with particular properties. But it’s also largely a trial-and-error process, because there is not yet any way to perfectly predict how
How to predict the behavior of molecules from scant data Read More »
Zyphra has released ZYFA (Zyphra FlashAttention on AMD), a set of FP8 and BF16 prefill attention kernels for AMD Instinct MI355X GPUs. ZYFA is Zyphra’s FP8 attention engine for long-context prefill, and the code is open source under Apache 2.0. On real model activations, its FP8 kernels run 1.16-1.76x faster than AITER, AMD’s default kernel
Zyphra ZYFA: FP8 FlashAttention for AMD MI355X, Up to 1.76x Faster Read More »
Artificial intelligence is reshaping industries across the board, and dentistry is no exception. From diagnostic imaging to patient communication, AI-powered tools are finding their way into modern dental practices at a remarkable pace. As these technologies become more accessible, both […] The post Can AI Improve Treatment Planning in Dentistry? appeared first on Techspective: A
Thinking Machines Lab has released Inkling 2 Small, the first model of its second Inkling generation. The Inkling 2 Small model is a sparse Mixture-of-Experts (MoE) with 594B total and 17B active parameters. It accepts text and images, and supports variable reasoning effort. On the Artificial Analysis Intelligence Index, it scores 31. Its predecessor, Inkling
Thinking Machines Releases Inkling 2 Small, a 594B MoE With 17B Active Read More »
Baidu has released ERNIE 5.5 Flash Base, the raw pre-training checkpoint of its new sparse Mixture-of-Experts language model. ERNIE 5.5 Flash Base is a 280B-parameter text model from Baidu that activates 14B parameters per token. The weights stop at the end of pre-training, with no mid- or post-training applied. This as a clean starting point
Baidu Releases ERNIE 5.5 Flash Base: A 280B MoE Base Model With 14B Active Parameters Read More »
Together AI has introduced Together Compiler (TKCC), an agent-driven system that keeps re-optimizing inference as production traffic changes. Together Compiler already runs on several of Together’s serverless endpoints. The core claim for developers: an engine tuned once goes stale, so tuning should never stop. TL;DR System: It is an optimization system, tested on Kimi K3,
Together AI Releases Together Compiler: Agents Make Inference Up to 2.6x Faster Read More »
Google Research has released Agile Deliberation, a human-in-the-loop framework for building image classifiers around subjective concepts. Think ‘healthy food’, ‘inspiring artwork’ or clickbait in content moderation. Most tooling assumes users already know the concept boundary. Agile Deliberation assumes they do not, and helps them find it. TL;DR Framework: It prompts Gemini 2.5 Pro and Gemini
Google AI Research Releases Agile Deliberation Framework for Gray-Area Image Classifiers Read More »
In an emergency, a human might someday ask a robotic assistant to fetch a wall-mounted defibrillator located down the hall. But if the robot has incorrectly labeled the defibrillator as a fire extinguisher in its stored memory, it may not know where to find the life-saving device.This robotic assistant could benefit from a new memory
webAI has released TwIL-8B, an 8.8B reasoning model for math, code and instruction following. The TwIL-8B reasoning model is post-trained from IBM’s Granite 4.2 8B. Weights are on Hugging Face under a non-commercial license. webAI’s launch post frames the pitch around cost per task, not raw scale. The 4-bit build is 4.98 GiB, sized for
webAI Releases TwIL-8B, an 8.8B Reasoning Model Scoring 98.2 on MATH-500 Read More »
