Run the newly released Gemma-2b 1.1 on LlamaEdge.

Lightweight runtime + lightweight model == perfect LLM app for the edge

Try it: …7d8c4d7c644ed19e85d0fd647.gaianet.xyz

Run it yourself: secondstate.io/articles/gemma…

* No Python dependency
* Native GPU speed
* OpenAI compatible API server out of…

wasmedge You can also check out this link: github.com/sohankunkerkar… that covers the integration with CRI-O

Finally, run binary-portable AI apps in Kubernetes across different OSes, CPUs, and GPUs. Instead of a different container image for each platform, you can now run a single wasm file on all devices — thanks to this PR merged upstream in crun yesterday. github.com/containers/cru……

See you in a few hours! There are some really exciting AI demos in our April community meeting!

Wow, love to see WasmEdge as the runtime for the underlying LLM!

github.com/OpenInterprete…

Very impressed by this project!

If you are at #KubeCon EU in Paris, stop by our booth!

And make sure you go to the workshop at 4:30pm this afternoon!

“Cloud Native WebAssembly and How to Use It” - Brooks Townsend, Cosmonic & Michael Yuan, Second State at KubeCon + CloudNativeCon Europe 2024…

Mark your calendar for WasmEdge community meeting trmr!

* Lightweight & cross-platform AI inference with multimodal LLMs by dm4

* Deploy WasmEdge functions on Civo by Saiyam Pathak

* Google Summer of Code opportunities with WasmEdge by hydai

Do not miss it!

LlamaEdge 0.4 is here!

🚀 Multimodal Visual Language Models
🚀 RAG-based “assistant” API
🚀 Faster and easier to get started

👉 secondstate.io/articles/llama…

Run #Llava : the multimodal VLLM on WasmEdge! Portable 2MB binary that runs on any CPU or GPU device. The video shows it running on a Nvidia server. You can run it on your MacBook without any change.

Rust source code for the app: github.com/second-state/W…

Haotian Liu

The best “small” LLM I have seen! Besides a MacBook, it could easily fit into a Jetson Nano, Orange Pi, or even Raspberry Pi. Edge LLM is coming.

llamaedge.com

Google’s brand-new open-source LLM, Gemma, is impressive. Even at 2b, a size that fits into IoT devices, it can write code. See below for Gemma 2b coding from a spec, & generating json - all on a MacBook using WasmEdge.

Run it on your own laptop: secondstate.io/articles/gemma…

Great news! Check out CNCF WasmEdge's #GSoC project ideas👉 github.com/cncf/mentoring…

wasmedge

Join #LamdaConf for wasmedge's talk Fast And Portable #LLM Inference With #WebAssembly And #Rust ⬇️
lambdaconf.us/speakers/micha…

Join us in May for the ultimate developer retreat in the Rockies, Colorado. LambdaConf!

LambdaConf is expanding beyond Functional Programming into Mainstream, AI, Distributed Systems, Durable Computing, WASM and more!

Starting on the weekend of 4-5 May with fun activities,…

LlamaEdge is not just a lightweight and portable runtime for chatbots. It is an app dev platform for portable LLM apps! RAG chatbots and AI agents can be developed on Mac or Windows, compiled to Wasm, and then deployed across Nvidia / AMD / ARM devices, fully taking advantage of…

Last call! Submit your application today!