How to build and run SpinApp on Azure Kubernetes Services (AKS) with SpinKube in 3 steps 🤞

Check it out 👉 dev.to/thangchung/how…

Fermyon SpinKube spinframework Matt Butcher @FermyonTech Radu Matei home skillet (@[email protected]) Mossaka Sven Pfennig @[email protected] Sohan

✍️ I did a sketch to explain WASM “pre-optimization” or snapshotting like you would find in Bytecode Alliance’ Wizer.

I’m very excited about these approaches for performance improvements, not just for the Web, outside the browser as well!

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…

Wow. #WebAI folk are fast! #Llama3 8B model already ported to run entirely in the web browser, client side, on device. Capture below is from my NVIDIA 1070 GPU (quite old now) + still runs fast enough! Incredible work by MLC folk (hat tip to Charlie Ruan) webllm.mlc.ai

Can't wait to see it's support come up with Pieces for Developers
Will be an amazing model for local privacy focused work!

Llama 3 is live!

Is it weird that I'm even more excited for the fine-tunes Teknium (e/λ), Nous Research, Eric Hartford, and others will cook up 👀?

llama.meta.com/llama3/

New Dart Package⚡

[ runtime_native_semaphores 0.0.5 ]

This package enables efficient cross-process and cross-isolate synchronization in Dart, using native semaphore mechanisms. It's essential for coordinating shared resource access without conflicts, ensuring robust and

Snowflake just released Arctic Embed, a collection of open-source text embedding models optimized for retrieval accuracy and efficiency! ❄️

📄 Apache 2.0 license
🌐 Great for in-browser use w/ 🤗 Transformers.js (22 → 335 M params)
⚡️ WebGPU-accelerated (>120x faster than WASM)

✨ Our latest release of GPTScript_ai v0.5 simplifies the management of credentials ✨ Read all the details about the updates available in this blog post here ➡️⬇️ buff.ly/4aT5WTg

#AI #LLM #GPTScript

The competition in AI music generation is heating up, with Suno and Udio leading the way. Unfortunately, neither are open source... 😢

Luckily, MusicGen is! 😍 The quality is amazing and you can even run it locally in your browser with Transformers.js! 🎵 For example:

prompt:

The Gemini API cookbook is shaping up quite nicely (and we just crossed 1k stars ✨)

Check it out if you want to quickly test out 1M context and native multi modal support!

github.com/google-gemini/…

💥We’re finally back with another AMA Livestream this WEDNESDAY at 9:30 AM EST to chat about our new Visual Studio extension and open source CLI agent!

We’re excited to answer any questions or feedback you might have! Access the livestream via YouTube, Instagram, Facebook, X &

Introducing MusicGen Web: AI-powered music generation directly in your browser, built with 🤗 Transformers.js! 🎵

Everything runs 100% locally, meaning no calls to an API! 🤯 Served as a static website... this costs $0 to host and run! 🔥

Try it out yourself! 👇

Introducing Our Speakers!! 🚀
We're thrilled to introduce our lineup of expert speakers who will be sharing their insights and knowledge during our upcoming ML Study Jams!✨🚀

🔥 Reserve your spot now to engage with our speakers and enhance your ML skills!

🏪 Excited to announce XState Store!

→ Extremely simple API
→ Extremely small (< 1kb min/gzip)
→ XState-compatible (if you need the power)
→ Extra strong typing (inferred!)

npm i @xstate/store

Join us next Wednesday for an AMA livestream showcasing our new Visual Studio extension and open-source CLI agent! 📅

We'll cover the features and benefits of each, and show you how to use them to improve your development workflow🦾

Get notified: youtube.com/watch?v=feg1ao…

We just dropped 2 new Google Gemma open models.

Based on our original pre-trained Gemma models, CodeGemma brings powerful code completion and generation.

RecurrentGemma leverages RNNs and local attention to improve efficiency. Check it out!

developers.googleblog.com/2024/04/gemma-…

Great time presenting today at #GoogleCloudNext teaching everyone about #VisualBlocks custom nodes! If anyone has questions after feel free to drop me a DM or such!

New Google developer launch today:

- Gemini 1.5 Pro is now available in 180+ countries via the Gemini API in public preview
- Supports audio (speech) understanding capability, and a new File API to make it easy to handle files
- New embedding model!

developers.googleblog.com/2024/04/gemini…

backend agnostic server-side rendering of web components? yep, it is possible 🌅

(desirable even. most elements are not client-side interactive…and most workloads aren't coming from a JS runtime)