E2EE ML primitives and runtime
INTELLECT-2: The First Globally Distributed Reinforcement Learning Training of a 32B Parameter Model
Today we are launching INTELLECT-2: the first 32B parameter globally decentralized Reinforcement Learning training run where anyone can permissionlessly contribute their heterogeneous compute resources.
.png?v=intellect-2)
Triton: A dynamic binary analysis library
Triton: A dynamic binary analysis library
Epistrons: Knowledge Artifacts for Hyperproblems - Hyperproblems
Overview - GroqDocs
Fast LLM inference, OpenAI-compatible. Simple to integrate, easy to scale. Start building in minutes.
Introducing Lea | Chinmay Hegde | 23 comments
Today we are releasing Lea. Lea is a powerful, open-source Lean 4 theorem proving agent, built out of DARPA's expMath program. Lea is a (deliberately minimal) agent designed to keep mathematicians in the driver's seat: a full front-end UI, full control and visibility on the back end, and a lovely Overleaf extension that auto-formalizes Latex to Lean while you continue working on your manuscript. Lea is fully open-source; we want everyone to fork it, break it, and tell us how to improve it. We have been using Lea internally within our academic groups for the last 3 months. It has closed and formalized multiple open problems in mathematics, and specifically a long-standing conjecture in nonlinear elliptic PDEs. (More on this soon!) We are at a pivotal time in mathematics. I have joked to my friends that DARPA expMath is a "tell-your-grandchildren-about-it" program. The kickoff room in DC in March had Fields medallists, Turing award winners, top mathematicians and theoretical computer scientists. It also had every serious startup in this space --- Axiom Math, Harmonic, Math Inc, @Principia labs, Logical Intelligence. Patrick Shafto and DARPA made a bold bet on AI-accelerated mathematical discovery, and not even 6 months later these efforts are already bearing fruit. Huge thanks to my collaborators Claudio Silva, Sam Westrick, Eduardo Teixeira, Jaume de Dios Pont, Daniel Arturi, Shashwat Patel, Kevin Gomez, and many others. Much of Lea is the result of their hard work, and it's a joy to work with them. | 23 comments on LinkedIn
Reverse-engineering GGUF | Post-Training Quantization
Kimi K2 0711 - API Pricing & Benchmarks
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. $0.57 per million input tokens, $2.30 per million output tokens. 131,072 token context window, maximum output of 32,768 tokens. Includes independent benchmarks from Artificial Analysis.
miniKanren, live and untagged: quine generation via relational interpreters (programming pearl)
As part of the Digital Library's transition to Open Access, new features for researchers are available in the Premium Edition. Click here to learn more.
Defining the common primitive — Tonk
Our beta test results have shown that Tonk's system for small software was one of many use cases, and that there is a common primitive between them all. A tonk space is data at a link, with its structure, views and rules. People, agents and systems read and write it with the permissions in the link.
Post-Training 50x Faster
We're announcing Trellis, the fastest open-source post-training code for Kimi K2 Thinking
