At its core, MCP follows a client-server architecture where multiple services can connect to any compatible client. Clients are applications like Claude Desktop, IDEs, or AI tools. Servers are light adapters that expose data sources.
SOFTWARE
-
Anthropic Introduces Model Context Protocol for LLM Data Integration
By
–
Introducing the Model Context Protocol (MCP) An open standard we've been working on at Anthropic that solves a core challenge with LLM apps – connecting them to your data. No more building custom integrations for every data source. MCP provides one protocol to connect them all:
-
SambaNova Cloud Empowers Developers at Every AI Journey Stage
By
–
We wanted you to hear from the team that made SambaNova Cloud possible 📣
— SambaNova (@SambaNovaAI) 25 novembre 2024
Our Director of Solutions Engineering, @ro_mattern, shares why she's excited about being able to reach #Devs at every stage of their #AI journey. 🎥
Start developing today ⤵️We wanted you to hear from the team that made SambaNova Cloud possible Our Director of Solutions Engineering, @ro_mattern
, shares why she's excited about being able to reach #Devs at every stage of their #AI journey. Start developing today -
SmolLM: Open Source Language Model Training and Deployment
By
–
SmolLM – run, pre-train, fine-tune, evaluate SoTA fully open source LM Run with Transformers, MLX, Transformers.js, MLC Web-LLM, Ollama, Candle and more! Apache 2.0 licensed codebase – go explore now!
-
Share Your Code: Community Contributions Welcome
By
–
Any code to share? Would love to see and share!
-
Production tips for open and closed source AI
By
–
a lot of alphas in this fresh unreleased slide-deck by @NielsRogge (well now it's released hahah – sorry Niels) production uses/tips for open and closed source AI https://
docs.google.com/presentation/d
/1LwiPxriVRulQtxsLPck2G8Ya_eMjx08lsXL7TVkRnKo/edit?usp=sharing
… -
Serving ChatGPT to 100M users with 1k H100s efficiently
By
–
Load balancing, caching, dynamic batching… with 10% DAU you probably don’t need much more than 1k H100s to serve ChatGPT to 100 million customers.
-
Optimizing llama.cpp quantization performance gains
By
–
good reminder: I need to check my llama.cpp quants I suspect I’m leaving perf on the table.
-
PhD Opportunity in Self Sustaining Software Systems
By
–
PhD Opportunity to work with Christian Cabrera and me on Self Sustaining Software Systems.
-
Apple Releases Fast CoreML Models for iPhone Performance
By
–
Pretty cool! @Apple released blazingly fast CoreML models AND an iOS app to run them on iPhone! ⚡
— Vaibhav (VB) Srivastav (@reach_vb) 23 novembre 2024
> S0 matches OpenAI's ViT-B/16 in zero-shot performance but is 4.8x faster and 2.8x smaller
> S2 outperforms SigLIP's ViT-B/16 in zero-shot accuracy, being 2.3x faster, 2.1x… pic.twitter.com/p9hPoajOtvPretty cool! @Apple released blazingly fast CoreML models AND an iOS app to run them on iPhone! > S0 matches OpenAI's ViT-B/16 in zero-shot performance but is 4.8x faster and 2.8x smaller > S2 outperforms SigLIP's ViT-B/16 in zero-shot accuracy, being 2.3x faster, 2.1x