GOSIM Conference 2024 Europe
| title | author | length |
|---|---|---|
| Moly - A pure Rust Explorer for Open Source LLMs | Jorge Bejar | 57m |
A desktop app that runs open‑source LLMs locally, built entirely in Rust + Wasm with a swap‑in .wasm model runtime and a Rust backend that registers three… | ||
| dora-rs: Modern Dataflow for Robotics | Xavier Tao | 27m |
dora-rs is a Rust robotics framework that runs nodes and publish/subscribe edges, uses Arrow zero-copy for cross-language messages and achieves ~2 ms… | ||
| The Future of APP Development | Dioxus Al | 39m |
Builds a Dioxus-specific copilot by fine-tuning open models (LoRA on Llama family) with a synthetic dataset: ~8,000 format-following generations produced 1,500… | ||
| Write One Run Anywhere, But for GPUs | Hydai Tai | 30m |
LlamaEdge compiles Rust (or C/C++/Go) apps to wasm bytecode and runs them on the LlamaEdge runtime built atop WasmEdge, routing WASI calls to native backends… | ||
| Fostering Responsible AI:Empowering Openness and Community Collaboration | Anni Lai | 29m |
Generative AI Commons presents the Model Openness Framework (MOF) that inspects 16 artifacts of a model lifecycle and ranks models into class one/class… | ||
| OminiX - Unified Acceleration Framework for Both LLM and SD GenAl Models on the Edge | Wang Yanzhi | 31m |
OminiX is an open-source runtime that unifies acceleration for Stable Diffusion and LLMs (LLaMA2 7B/13B, Mistral 7B) with on-device finetuning and a common… | ||
| LLM for Coding, the State and lnitiative | Wei Lu | 40m |
Claims adoption numbers: GitHub Copilot yields about 30% acceptance rate for completions while a China internal tool sees ~80% internal adoption; model sizes… | ||
| nothing matches | ||