与「WebGPU」相关的搜索结果

有人用 Fable 5 开发单板滑雪游戏的第 10 天 🏂 现在游戏里有缆车了。没错，你当然可以在缆绳上滑行，一路火花四溅。 新增树木模型，降低了滑行动作的难度，还对 UI 做了大量优化。 完全使用原生 WebGPU 开发，没有使用任何游戏引擎。

Day 10 of building a snowboarding game with Fable 5 🏂 We have ski lifts now. And yeah, of course you can grind the cables, throwing sparks the whole way down. New tree models, easier grinds, and tons of UI work. All raw WebGPU, no engine.

离谱了兄弟们，GitHub 上刚扒出来一个神仙项目，直接把“剪映”干成了纯网页版。不用下载、不用传云端、连水印都没有，这波真有点狠！ 这玩意叫 OpenReel Video，是一个浏览器原生的专业级视频剪辑器。来自 GitHub 开源社区，目前已经狂飙将近 4000 星。最硬核的是它用了极其宽松的 MIT 协议，完全开源免费，没有任何套路。 核心卖点直接看： 🔥 即开即用：不用装笨重软件，打开网页就能剪。 🔒 绝对隐私：纯客户端运行，视频素材 0 上传，懂的都懂。 ⚡️ 性能炸裂：上了 WebGPU 硬件加速，网页里剪 4K 一样丝滑。 🎨 功能专业：多轨道、关键帧、LUT 调色全都有，媲美专业级。 💰 零成本白嫖：无广告、无订阅费、导出绝无水印，白嫖党狂喜。 不仅能独立用，它甚至还能直接嵌进 ComfyUI 的工作流里，对 AI 创作者来说简直是神器。 🔗 项目地址：

有人用 Fable 5 给 RL 训练出来的生物加了毛发和声音 声音不是录的，是直接从神经网络激活值生成的 JAX + MuJoCo 训练，three.js + WebGPU 渲染，看起来像某种活的东西在地板上爬 算艺术还是算研究？

Using Fable 5 to add fur and a new voice to my RL creature. The voice is based on the neural network activation (pictured top left). Made with @threejs @webgl_webgpu @runpod trained with JAX and MuJoCo from @GoogleDeepMind

The team cooked on performance. 'Everything the light touches' was optimized Simba. Painting, layout, WebGPU shaders, blocking scripts. Every frame scrutinized. The best part is that we'll be updating our with the lessons learned!

猛啊！在浏览器里跑 Gemma 4，堪比 ChatGPT？！🔥 完全零服务器、零数据上传、离线使用、纯WebGPU本地推理！ Xenova把 Fable 5写的27个自定义WebGPU内核 全部开源了： - Gemma 4 E2B（23亿参数移动优化版） - AI自己帮AI写低级WGSL着色器 - 速度从84直接拉到 255 tok/s（M4 Max / RTX 4090 上丝滑如本地App） 这玩意儿到底有什么用？ - 隐私党福音：处理合同、代码、聊天记录、敏感信息，数据永远只在你设备上，绝不上云 - 离线神器：飞机、高铁、地铁、没网也能随时聊天、写文、脑暴 - 秒回助手：日常问答、文档总结、代码生成、翻译、创意写作，响应快到飞起 - 开发者玩具：直接看AI生成的27个内核代码，学习WebGPU优化，fork改成自己的网页AI工具 - 未来模板：网页游戏实时NPC、在线文档智能助手、浏览器内实时翻译、个性化学习工具……全都能本地跑 这是 Agentic AI自我优化推理引擎 的真实落地！ Fable 5帮自己加速，结果第三天访问被暂停了…… 现在轮到我们普通人爽了⚡ 评论区见地址👇

Lightning-fast Multilingual TTS that runs entirely on your device! Supertonic is a lightning-fast, on-device multilingual text-to-speech system designed for local inference with minimal overhead. The model runs via ONNX Runtime with 66M parameters. Generates speech up to 167x faster than real-time on consumer hardware. Complete privacy, zero network dependency, all processing happens locally. Supports 31 languages including English, Korean, Spanish, Portuguese, French, German, Japanese, Chinese, Arabic, Dutch, and more. Natural text handling without pre-processing. Directly processes numbers, dates, currency, abbreviations, and complex expressions. Performance on M4 Pro CPU: 1263 characters per second for long text, real-time factor of 0.012. WebGPU mode reaches 2509 characters per second. RTX 4090 hits 12,164 characters per second. Natural text handling works on financial expressions ("$5.2M" pronounced correctly as "five point two million dollars"), time and dates ("4:45 PM on Wed, Apr 3, 2024"), phone numbers with extensions, and technical units with abbreviations. All without phonetic annotations or text normalization. Voice Builder lets you turn your voice into a deployable TTS model with permanent ownership and edge-native deployment. Key capabilities: • Ultra-lightweight (66M parameters) • On-device inference with zero latency • Natural text handling without pre-processing • 31-language multilingual support • Cross-platform via ONNX Runtime • Up to 167x faster than real-time • Complete privacy - all local processing • Custom voice creation with Voice Builder • Expression tags for natural human nuance It's 100% Open source I've shared the link in the replies!

If you love fine-tuning open-source models (like me), then listen. > Start with 1B, 2B, 4B, and 8B models. (Don't start with a 27B model or bigger at first.) > Use WebGPU providers. I use Google Colab Pro for any model smaller than 9B. A single A100 80GB costs around $0.60/hr, which is cheap. Enough for small models. > Don’t buy GPUs unless you fine-tune 7 to 10 models. You'll understand the nitty-gritty in the process. > Use Codex 5.5 × DeepSeek v4 Pro to create datasets. Codex to plan, DeepSeek v4 Pro to generate rows. > Use Unsloth's instruct models as a base from Hugging Face. Yes, there are others too, but Unsloth also provides fast fine-tuning notebooks. > Use Unsloth's fine-tuning notebooks as a reference. Paste them into Codex, and Codex will write a custom notebook with the configs you need. > Spend 1 day learning about: - SFT (supervised fine-tuning) - RL training (GRPO, DPO, PPO, etc.) - LoRA / QLoRA training - Quantization and types - Local inference engines (llama.cpp) - KV cache and prompt cache > Just get started. Claude, Codex, and ChatGPT can design a step-by-step plan for how you can fine-tune your first AI model. Future tech is moving toward small 5B to 15B ELMs (Expert Language Models) rather than general 1T LLMs. So fine-tuning is an important skill that anyone can acquire today. Tune models, test them, use them. Then fine-tune for companies and make a career out of it. (Companies pay $50k+ to fine-tune models on their data so they can get personalized AI models.) Shoot your questions below. I'll be sharing in-depth raw findings about this topic in the coming days.

建筑师们肯定会对此感到“抓狂”。有人刚刚开源了一个完全运行在浏览器中的全功能 3D 建筑编辑器。无需 AutoCAD，无需 Revit，也不需要每年 5,000 美元的授权费用。它被称为 Pascal Editor。它基于 React Three Fiber 和 WebGPU 构建——这意味着它直接在你的 GPU 上进行渲染，速度接近原生。以下是它的核心功能： → 一个完整的建筑/楼层/墙体/区域层级结构，支持实时编辑 → ECS 风格的架构，每个对象都通过 GPU 驱动的系统进行更新 → 集成了完整撤销/重做功能的 Zustand 状态管理 → 基于 Next.js 的前端，因此它作为 Web 应用部署，而非桌面安装版 → 脏节点追踪（Dirty node tracking）——仅重新渲染发生变化的部分，而非整个场景 最令人惊叹的部分在于：你可以对单个建筑楼层进行堆叠、拆解或单独查看。选择一个区域，拖动一面墙，重塑一个楼板——全部在 3D 环境中，全部在浏览器中完成。 建筑事务所为实现这种工作流的 BIM 软件，每个席位的费用高达 5 万美元以上。而这个是免费的。100% 开源。