Search fresh public links, source activity, and ready-to-use post angles for Onnx.
Fresh curated links around ONNX are collected here so marketers can spot useful updates and turn timely ideas into posts faster.
Recent items include:
Recent curated links from global sources. Generate one free draft from any story, then use SocialBu to schedule and refine your content calendar.
Artificial Intelligence has become one of the most influential technologies in modern software development. From chatbots and recommendation systems to sentiment analysis and intel...
The UXL Foundation announced today the release of oneDNN 3.14 as the latest feature update to this library providing optimized deep learning operations for software like PyTorch, T...
The first version of Microsoft-Decision-1 is based on Qwen3.5-9B, but the next will sport homegrown tech, Redmond reassures
StartLux open-sourced Prism, an inference engine rebuilt for decision models. On one H200, it reports up to 5.3x faster multi-question runs, 41 ms average latency and bit-identical...
SenseTime's SenseNova U1.5 is an 8B Mixture-of-Transformers native unified vision model—no external encoder/VAE—with up to 4K generation and open SFT/RL/distillation training code.
Shanghai AI Lab's Intern-Decision comes in 0.8B, 2B and 4B sizes and returns choices, scores and yes/no answers with probabilities; MetaX shipped Day-0 support.
Компании AMD и Intel договорились объединить свои наработки по оптимизации PyTorch в открытой библиотеке глубокого обучения oneDNN. Эта библиотека развивается под эгидой фонда Unif...
Перед каждым ML-разработчиком, после обучения прекрасной модели, которая поднимет бизнесу метрики, а тебе годовую премию, возникает вопрос: а как ее задеплоить в сервисе, чтоб она...
Nokia’s applied research team has open-sourced AnyJev, a Python library that turns an open LLM into a decision model. It needs no training. It targets a common production job: pick...
Ant Group and the vLLM community open-sourced Humming, a JIT GEMM kernel library for quantized inference. It covers INT1-8 and FP4-FP8 mixes and fully supports T-Head's Zhenwu 810E...
Learn how to leverage NVIDIA’s cuDNN Frontend Graph API to build custom kernel fusions, autotuning engine configurations, FP8-style epilogues, scaled dot-product attention, dynamic...
Use SocialBu to discover ideas, generate post drafts, and schedule them across your social channels.