Submissions by 3Sophons

Write Once Run Anywhere, but for GPUs

Wikimedia Slashed 300ms Off Every WASM Execution with WasmEdge

Run with Phi 3.5-mini across GPUs, CPUs and OSes

Linus at KubeCon+OSSummit: Will Rust Secure a Bigger Role in the Linux Kernel?

Linus at KubeCon+OSSummit: AI's Value in Software Development is Code Review

KubeCon and CloudNativeCon and Open Source Summit and AI_dev China 2024

Open Source LLM-Gemma Powered Agentic Research Assistant

LLM Tool Call Demo: Finetuned Llama3 Invokes Python Code& Manipulates Data on PC

Run Llama 3.1 on any device. Embed Llama 3.1 in any app

Run Llama 3.1 on any device. Embed Llama 3.1 in any app

Embed LLMs in your app easily–each model tackles agentic tasks it finetuned for

Can the New Mathstral LLM Accurately Compare 9.11 and 9.9?

WebAssembly on Kubernetes: The Practice Guide

Run across devices open source LLMs like Phi-3 and get a API server in mins

Demo: Run the 314B Grok LLM on Pure CPU with WASM?

Efficient and Portable AI / LLM Inference on the Edge Cloud

Create an LLM web service with LlamaEdge on MacBook, deploy it on Nvidia devices [video]