AI BriefingFuriosaAI news
The latest AI and developer news from FuriosaAI, with short summaries.
Visit website →Furiosa SDK 2026.1: Hybrid Batching, Prefix Caching, Native Kubernetes Support
Furiosa SDK 2026.1 strengthens batching, caching, and Kubernetes support.
FuriosaAI Begins Mass Production of RNGD for Data Center AI
FuriosaAI has started mass shipments of RNGD, marking its full-scale entry into the enterprise AI inference market.
Holistic Optimization of AI Inference Systems
Lowering AI inference costs requires optimizing every layer, from the model to scheduling.
How PyTorch Handles Dynamic Tensor Shapes
torch.compile recompiles when shapes change and restricts execution scope using guards.
Serving GPT-OSS 120B on RNGD at 5.8ms TPOT
Two RNGD cards served GPT-OSS 120B at 5.8ms TPOT with low power consumption.
FuriosaAI SDK 2025.3 Brings Major Performance Boost to RNGD
With SDK 2025.3, RNGD achieves 3x throughput and a 35% improvement in TTFT on Llama 3.3 70B.
FuriosaAI Unveils RNGD Server for Efficient AI Inference
FuriosaAI has unveiled the 'NXT RNGD Server,' a turnkey solution for AI inference optimized for existing data center infrastructure.
FuriosaAI and OpenAI: The Future of Sustainable AI
At the OpenAI Seoul office opening event, FuriosaAI demonstrated its AI accelerator **RNGD** efficiently running the **gpt-oss-120b** model.
FuriosaAI Presents Papers on AI Performance at ICML and ACL
FuriosaAI presented 6 research papers at ICML and ACL that enhance model efficiency, reasoning capability, and flexibility.
FuriosaAI Raises $125 Million Series C to Scale AI Computing
FuriosaAI has raised a $125 million Series C round to scale AI computing.
LG AI Research Achieves 2.25x Improvement in LLM Inference Performance
LG AI Research adopted FuriosaAI's RNGD accelerator, boosting LLM inference efficiency for its EXAONE models by 2.25x compared to GPUs.
Furiosa SDK 2025.2: Hugging Face and Reasoning Model Support
Furiosa released SDK 2025.2 for RNGD, strengthening reasoning model support and Hugging Face integration.
FuriosaAI Launches RNGD on Microsoft Azure Marketplace
FuriosaAI's AI accelerator **RNGD** has launched on Microsoft Azure Marketplace, supporting easy AI infrastructure deployment for enterprises.
Building RAG Applications with RNGD | FuriosaAI
Presents how to build a high-performance, low-power RAG application using FuriosaAI's RNGD accelerator.
AI Agents: Core Concepts and Capabilities
AI agents are the next-generation AI paradigm that goes beyond the limitations of LLMs to enable autonomous problem-solving.
Furiosa SDK 2025.1.0 Released
Furiosa has released SDK 2025.1.0, which optimizes LLM inference performance and supports Tool Calling.
FuriosaAI Demonstrates High-Speed Inference Performance Using Furiosa SDK
FuriosaAI demonstrated high-speed batch inference performance that efficiently processes large-scale LLM requests through its RNGD chip and SDK.
FuriosaAI: The Future of AI Lies in Efficient Inference
As the AI industry shifts from training to inference, the importance of efficient inference computing is growing.
FuriosaAI Presents Papers at ECCV and CoLM Conferences
FuriosaAI presented research papers on multimodal learning and diffusion model control at ECCV and CoLM.
A New Chapter for Kubernetes and ML Inference
Kubernetes supports hardware optimization and efficient management for ML inference through **DRA** and **CDI**.