An AlphaGo Moment for Inference?
INT21 generated 20 inference engines across seven model categories in two weeks using Rust with C++ and CUDA components, and its MiMo engine reached 1,308 tokens/s versus 540 for tuned SGLang and 1,01…
INT21 generated 20 inference engines across seven model categories in two weeks using Rust with C++ and CUDA components, and its MiMo engine reached 1,308 tokens/s versus 540 for tuned SGLang and 1,01…
SwarmOS, backed by GPT-6 Astra, generated a Rust/CUDA fully sharded data-parallel trainer for Qwen3.8-27B that achieved over 11.5× higher throughput than the eager PyTorch FSDP2 baseline and 21.5% hig…
INT21's SwarmOS infrastructure orchestration platform achieved a 100% RHAE score on the ARC-AGI-3 Public benchmark using only GPT-5.6-Sol, up from the model's official 13.3%, a 7.5x improvement, and a…
INT21's agent swarms have built inference stacks for video, music, and speech generation, now live as free demos without an API key. The stacks require no human review and outperform state-of-the-art …
INT21 defines a new category called Self-Improving Compute Infrastructure, where AI agent swarms continuously improve the software that AI runs on, starting with GPU kernels. The company argues that i…
Meta released Muse Spark 1.1, a multimodal reasoning model for agentic work, alongside the public preview of the Meta Model API. INT21 tested the model in a Swarm research system with 29 agents proces…
INT21 has built SwarmOS, a cloud-native platform for multi-agent AI systems, arguing that orchestrating specialized agents is more effective than relying on larger context windows. The company demonst…
INT21 launched as the first company to achieve self-improving AI agent swarms for AI infrastructure, introducing PTX Kernel Factory that generates and optimizes low-level GPU software for NVIDIA hardw…