This project is valued at over $1 billion dollars in the most recent round last month. Maybe I do not understand the meaning of “all services are online”

Microsoft Phi3 is coming, if you want to inference Phi3-mini model , please read my blog aka.ms/phi3gettingsta… 🥳🥳🥳🥳🥳 #phi3 #SLM #wasmedge ollama Second State

New video is out - Run Llama 3 locally using Ollama and LlamaEdge
Llama3 using Ollama.
Loved Ollama, Also shown the Web UI in the video along with how to run it using Wasmedge via the llamaedge project.
Go check out now!

🚀 Exciting news! LlamaEdge 0.8.4 supports Phi-3-mini-4k! It can write #Rust code for me.

Ready to dive into the Microsoft new high perfomance model? Simply execute this one single command on your device:

bash <(curl -sSfL 'raw.githubusercontent.com/LlamaEdge/Llam…') --model phi-3-mini-4k

Let…

🚨ICYMI: The WasmEdge runtime was recently added to openSUSE Linux #Tumbleweed 🚨

Join Divya Mohan as she hosts Michael Yuan, CEO of Second State, on an upcoming episode of Rancher Live to demystify what this means for #cloudnative #wasm workloads🎙️

🕙: 10 AM ET
🗓️: May 9, 2024
📍:

Llama3 running on LlamaEdge 🚀

Run it on your own computer or edge device on any GPU, CPU or accelerator. Extend it with your own code for prompt management, RAG and function calling.

github.com/llamaedge/llam…

Places I have been to in the past month. On the road again. See y’all soon.

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…

Watched the Great American Eclipse in Dallas. None of these photos are AI generated. They are unfiltered from my iPhone. p2 is the “diamond ring” — the moment the Sun is “turned back on” — it is one of the most striking experiences you can have.

Great examples on how to run Wasm and AI apps in the CRI-O stack!

A small step for Kubernetes. A big step for running cloud-native LLM apps!

GaiaNet proudly presents our esteemed partners, ByteTrade Lab & UC Berkeley (University of California Berkeley FHL Vive Center)!

Read our official PR here 📢
news.bitcoin.com/bytetrade-lab-…

◣ GaiaNet is a decentralized network that provides secure, censorship-resistant, and…

Don't miss Michael Yuan's talk at #LambdaConf2024 !

Learn how #WebAssembly and #Rust enable fast and portable LLM inference, eliminating
#Python dependencies and delivering lightweight, cloud-safe functions.

Get your tickets now: buff.ly/3wbaG7U

#AIInference #Wasm

Checkout this video from hydai showing it answering the question “What is WasmEdge” on a WasmEdge runtime.

The metaphysical.

x.com/hydai_tw/statu…

David meets Goliath. WasmEdge runs the #Grok 314B model. Since we literally do not have a GPU that big, we decided to run it on CPU machine!

Grok is released as a base model. So we just asked it to complete a sentence: “Elon Musk brought Twitter because ”

It answered…

It's a wrap! Another great Wasm I/O edition in the books 💪. Thanks to everyone who made it possible, see you all in 2025 (27-28 March) 🚀

This is a video of the demo of running an ELF binary of a Neural Network for training MNIST converted to WASM by elfconv using WasmEdge runtime.

from 0:25
#wasmio24

Full house for our first workshop 'Efficient and portable AI / LLM inference on the edge cloud' by Michael Yuan #wasmio24

The UT Austin Texas Football flag in the American Club in Singapore.