Explore tweets tagged as #torchchat
PyTorch just released torchchat, making it super easy to run LLMs locally. 🔥 - Supports a range of models, including Llama 3.1. - Can use it on servers, desktops, and even mobile devices. - pretty straightforward to implement - offers both Python and native execution modes.
10
134
647
Chat with LLMs Everywhere torchchat is a small codebase showcasing the ability to run large language models (LLMs) seamlessly. With torchchat, you can run LLMs using Python, within your own (C/C++) application (desktop or server) and on iOS and Android. https://t.co/JPRV8r04HO
0
6
11
🔥PyTorch releases its own LLM solution called torchchat. torchchat allows you to chat with a variety of open models and it even includes a UI to chat with LLMs on the browser. Supports running models on a desktop/server and on mobile. torchchat is a native-PyTorch library
4
122
491
Introducing torchchat 🔥 A lightweight library to run LLMs locally across mobile, desktop and laptops powered by PyTorch. Learn more: https://t.co/MhRTSxPsPg
#llms #mobilellms #localai #pytorchllm #edge #ondeviceai
16
189
875
pytorch llm'ler ile ilgili süper geliştirmeler yapıyor. sonuncusu: torchchat büyük dil modellerini çeşitli cihazlarda çalıştırmak için yeni çıkan bir kütüphane. torchchat, llama 3, 3.1 gibi modelleri laptop, masaüstü ve mobil cihazlarda sorunsuz ve verimli bir şekilde
1
7
65
New low-bit embedding and linear operators for Arm CPUs are now in TorchAO, PyTorch’s low-precision library! Compatible with eager, torch.compile, AOTI, and ExecuTorch, they’re built for flexibility and ready for #torchchat. 👋Learn more: https://t.co/YkTKm2mrz3
#pytorch
2
37
191
Run torchchat by @PyTorch on Android and iOS ( https://t.co/IQTyMWmX1S) With torchchat, you can run LLMs on iOS and Android
0
5
39
𝐭𝐨𝐫𝐜𝐡𝐜𝐡𝐚𝐭 - 𝐏𝐲𝐓𝐨𝐫𝐜𝐡 𝐛𝐚𝐬𝐞𝐝 𝐋𝐋𝐌 𝐢𝐧𝐟𝐞𝐫𝐞𝐧𝐜𝐞 𝐥𝐢𝐛𝐫𝐚𝐫𝐲 torchchat is a lightweight library to run LLMs locally across mobile, desktop and laptops powered by PyTorch. torchchat achieves more than 8Tokens per second on the Samsung Galaxy S23 and
0
0
3
@bushontheradio LED Lenser H7R. Rechargeable, different brightness settings, adjustable angle. Eats batteries if you run it for a while. I normally flatten a set of 4 AAA’s in an 8 hour shift. Good kit 👌🏻#TorchChat
1
0
1
𝐓𝐨𝐫𝐜𝐡𝐜𝐡𝐚𝐭 𝐚𝐧𝐝 𝐒𝐐𝐋𝐢𝐭𝐞-𝐕𝐞𝐜 𝐚𝐫𝐞 𝐢𝐧 𝐭𝐫𝐞𝐧𝐝𝐢𝐧𝐠 𝐓𝐨𝐫𝐜𝐡𝐜𝐡𝐚𝐭 : PyTorch Torchchat is a recently introduced library that simplifies the process of running LLMs locally on a variety of platforms, including laptops, desktops, and mobile devices.
0
0
6
It's late and i spent most my day chasing a bug. It was a dumb bug but it felt good in some odd. I spend so much time managing things now that I rarely get to be technical. Miss the days when i often got to put my head down and just build. #torchchat #llama
0
0
3
🔥Llama 视觉模型终于来了！！！Meta 发布 Llama 3.2 系列 2+2！ 1⃣Llama 3.2 Vision（视觉模型）11B & 90B： 1）可平替同级别纯语言模型（Llama 3.1 8B 和 70B） 2）视觉任务媲美闭源多模态模型（Claude 3 Haiku 和 GPT4o-mini） 3）可通过 torchtune 微调 + torchchat 本地部署 2⃣Llama
📣 Introducing Llama 3.2: Lightweight models for edge devices, vision models and more! What’s new? • Llama 3.2 1B & 3B models deliver state-of-the-art capabilities for their class for several on-device use cases — with support for @Arm, @MediaTek & @Qualcomm on day one. •
3
35
79
torchchat experience is so painful when comparing to llama.cpp, the true Just Work (TM) no dependency shenanigans even the llama-server is just works
Just Work (TM): almost every python projects is a dependency nightmare
0
0
0
PyTorch just announced TorchChat, now enabling local LLM inference directly on your device. More control, enhanced privacy, and no reliance on the cloud. Perfect for developers looking to seamlessly integrate AI. Local LLMs FTW! https://t.co/YOb1g4uY5b
0
0
2
TorchChat diagram. Looks cool, but does it really help develop LLM applications?
1
0
0
Run PyTorch LLMs on any device with #torchchat! From servers to smartphones, experience seamless AI interaction. Is this the future of ubiquitous intelligence? 🤖💬 https://t.co/SnklLWLv20
0
0
0
torchchat Run PyTorch LLMs locally on servers, desktop and mobile. https://t.co/osWyk6B8DI
0
11
38
torchchat from @PyTorch makes it super easy to run LLMs locally. - Supports a range of models, including Llama 3.1. - Can use it on servers, desktops, and even mobile devices. - pretty straightforward to implement - offers both Python and native execution modes. It also
1
6
40
Torchchat from PyTorch, a library showcasing how to seamlessly and performantly run Llama 3, 3.1, and other large language models across laptop, desktop, and mobile. Blog: https://t.co/tsf1ngfrli Github: https://t.co/EMMVKzGjmt
0
1
1