部署工程

🚀 Excited to release LongLive 2.0! 🎬 An end-to-end infrastructure for long video generation, with FP4 and parallelism at the core of both training and inference. ⚡45.7 FPS generation speed on 5B model⚡ ✨ LongLive 2.0 supports real-video training, few-step distillation, multi-shot training/inference, sequence-parallel acceleration, NVFP4 KV cache, and async VAE decoding deployment. 🧩 To our knowledge, this is the first open-source 4-bit long video generation infra that covers both training and inference. 🙌 Welcome to check it out, try it, and share feedback! 🔗 Code: github.com/NVlabs/LongLive 📰 Paper: huggingface.co/papers/2605.1… 🎥 Demo: nvlabs.github.io/LongLive/Lo… #LongVideoGeneration #VideoGeneration #Realtime #AIInfra #EfficientAI #FP4 #Parallel #NVIDIA Video

We released experimental MTP Qwen3.6 Unsloth GGUFs! Qwen3.6 27B MTP now runs at 140 tokens/s. Qwen3.6 35B-A3B MTP gets 220 tokens/s generation on a single GPU. Qwen3.6 27B and 35B-A3B have >1.4x speed-up over the original GGUFs without any change in accuracy. Guide + GGUFs + Benchmarks: unsloth.ai/docs/models/qwen3… In terms of average speedup, we see a 1.4x for dense models at draft tokens = 2 and for the MoE around 1.15 to 1.2x. We do not recommend more than 2 draft tokens because the acceptance rate drops precipitously from 83% to 50% with 4 draft tokens, and the forward passes for MTP become less beneficial. Use `--spec-type mtp --spec-draft-n-max 2` Thanks to Aman for github.com/ggml-org/llama.cp…!

Damn！所有AI开发者，立刻停下你手里的npm install🤯 现在正在爆发有史以来最恐怖的供应链攻击， 代号Mini Shai-Hulud， 已经波及TanStack全家桶、Mistral AI、UiPath等170多个npm和PyPI包， 全是你们天天装的工具链， 周下载量加起来超过一个亿， 已经不是传统的维护者账号被盗了， 而是整个GitHub Actions CI管道被直接劫持， 合法的官方项目，自己发布了带毒的版本， 还带完整的SLSA 3级可信证明， 所有传统的签名验证全失效， 最狠的是它的持久化机制， 它不会只藏在node_modules里， 它会直接修改你的~/.claude/settings.json和~/.vscode/tasks.json， 就算你npm uninstall删光所有包， 只要你下次打开Claude或者VS Code， 它就会自动重新执行， 如果你敢撤销被盗的token， 它会直接删光你整个home目录， 而且它是蠕虫， 偷到一个项目的CI密钥，就会自动感染下一个， 现在还在指数级扩散， 以前我们说别用latest，别用^， 现在就算你pin死了版本， 只要那个版本是6分钟窗口期内发布的， 就是带毒的， 越依赖AI Agent自动装包的人， 这次中招的概率越高， 因为你的Agent根本不会帮你检查lockfile， 现在立刻做这三件事， 第一，冻结所有包安装， 第二，跑npx supply-chain-attack全盘自查， 第三，全量旋转你所有的云密钥、GitHub token和SSH key， 一个都别漏。 #网络安全 #npm #AI开发者

Today we’re launching the OpenAI Deployment Company to help businesses build and deploy AI. It's majority-owned and controlled by OpenAI. It brings together 19 leading investment firms, consultancies, and system integrators to help organizations deploy frontier AI to production for business impact. openai.com/index/openai-laun…

Introducing Pareto Code: a new, free, experimental coding router Set `min_coding_score` in your request and route to the cheapest code-capable model that clears your bar, ranked by @ArtificialAnlys. See the Pareto frontier shifting in real time👇

Today we’re launching the OpenAI Deployment Company to help businesses build and deploy AI. It's majority-owned and controlled by OpenAI. It brings together 19 leading investment firms, consultancies, and system integrators to help organizations deploy frontier AI to production for business impact. openai.com/index/openai-laun…