Agents
Opus 4.7 just wrote a custom WebGPU kernel that runs Qwen3.5 up to 13x faster using a fused LinearAttention op! 🤯 Agentic kernel optimizati…
Opus 4.7 just wrote a custom WebGPU kernel that runs Qwen3.5 up to 13x faster using a fused LinearAttention op! 🤯 Agentic kernel optimization is the future. Now live in 🤗 Transformers.js v4.2.0! P.S.
Opus 4.7 just wrote a custom WebGPU kernel that runs Qwen3.5 up to 13x faster using a fused LinearAttention op! 🤯 Agentic kernel optimization is the future. Now live in 🤗 Transformers.js v4.2.0! P.S. I've updated all our previous demos to use this new version. Enjoy! Media
Related
- Kimi K2.6 just entered the chat. > beats gpt 5.4 and opus 4.6 on coding. > open source. open weight. > 3x-5x cheaper. > really good for peop…
- Dataset Curation 3, this time agentic tool calling traces! https://huggingface.co/datasets/DJLougen/Acta
- انتهت Øجة 'ما عندي كرت شاشة قوي عشان أشغل ذكاء اصطناعي Ù…Øلي'. علي بابا نزلت موديل Qwen3.6 بهندسة MoE. Øجمه الكلي 35B (يعطيك ذكاء عالي جداً)،…
- Open-source agent for long-horizon deep research https://github.com/TIGER-AI-Lab/OpenResearcher
- Agentic Infrastructure
Source: Clem Delangue (X) | 2026-04-23