#ai inference
Ai Inference: 10 AI articles covering ai inference news, analysis, and research
Articles
Baseten's Base Labs Launches Open-Weight AI Safety Partnershipβ8
Baseten's Base Labs partners with Hugging Face and Goodfire to build open-weight AI safety infrastructure, tackling the rise of abliterated models and unsafe op...
Reducing HBM ECC Controller Overhead for AI Inferenceβ10
HBM ECC adds bandwidth and latency overhead for AI inference. Learn how on-die ECC and smarter controller design reduce that cost in high-bandwidth AI accelerat...
Architecting Memory and Storage in the AI Eraβ10
Explore how AI inference is reshaping enterprise infrastructure, demanding new memory and storage architectures for speed, scalability, and energy efficiency.
Open-Weight AI Companies Are the Hottest Acquisition Targets inβ9
Open-weight AI companies are becoming prime M&A targets, with Nvidia reportedly acquiring Hugging Face for $13B. Discover why tech giants are investing billions...
OpenAI's JalapeΓ±o Chip Delivers Breakthrough Inferenceβ7
OpenAI unveils JalapeΓ±o inference chip, showcasing breakthrough token throughput and efficiency gains over Nvidia Blackwell in early benchmarks.
OpenAI Unveils JalapeΓ±o Chip, Claiming Faster AI Inference Than Nvidiaβ8
OpenAI's new JalapeΓ±o chip outperforms Nvidia in AI inference benchmarks, marking a strategic move into custom silicon to cut costs and boost performance.
Starcloud Raises $250M to Build Orbital Data Centers as Launchβ9
Starcloud secures $250M to build orbital data centers, tackling launch bottlenecks as SpaceX phases out Falcon 9 for Starship.
Ramp Launches Its Own AI Model Router: What You Need to Knowβ9
Ramp launches Router, an AI model router with unified API access to top LLMs, free until 2027, featuring flexible routing strategies and a metrics dashboard.
Groq Secures $350M to Accelerate Neocloud Strategyβ9
Groq raises $350M led by Disruptive with Nvidia backing to expand its neocloud AI infrastructure, post-talent deal with Nvidia, aiming to scale data centers.
Kog Goes Deeper to Squeeze More Inference Out of GPUsβ9
Kog boosts AI inference speed on standard GPUs with software, claiming faster decoding on AMD and NVIDIA hardware.