#GPU Computing
12 articles with this tag
Most read in #GPU Computing, last 30 days
Together AI Refines Model Deployment
Together AI details its capacity-aware routing architecture for dedicated model inference, enabling dynamic deployments, A/B testing, and efficient scaling.
99.9% Uptime: What It Really Means for AI Inference
Achieving 99.9% uptime for AI inference means surviving data center failures, demanding active multi-facility traffic and direct infrastructure control.
Snowflake Unlocks Multiparty ML in Data Clean Rooms
Snowflake's ML Jobs are now generally available in Data Clean Rooms, enabling sophisticated, multiparty machine learning across organizations without sharing raw data.
Mozilla.ai Unveils transcribe.cpp
Mozilla.ai launches transcribe.cpp, an open-source C/C++ library for fast, GPU-accelerated speech-to-text inference with broad model support.
Databricks, NVIDIA Forge AI Partnership
Databricks and NVIDIA are deepening their collaboration, integrating NVIDIA's GPUs, Vera CPUs, and AI software to accelerate enterprise AI development and agentic applications on the Databricks Lakehouse platform.
Faster LLMs by Reshaping Sparsity
Sakana AI and NVIDIA unveil a new method that reshapes sparsity in LLMs to boost GPU efficiency, achieving over 20% speedups.
AI agents boost GPU kernels 38%
AI agents autonomously optimize GPU kernels, achieving 38% speedup and demonstrating potential for complex software development.
Cursor's Warp Decode Boosts MoE Inference
Cursor's new 'warp decode' technique dramatically boosts MoE model inference speed and accuracy on Blackwell GPUs by rethinking parallelism.
Vultr and the Sovereign Cloud AI Gap
Sovereign cloud decisions are failing to account for the actual compute needs of AI, creating a critical infrastructure gap.
DoRA Efficiency Breakthrough
New factored norm and fused kernels unlock DoRA's potential, delivering 1.5-2x speedups and significant VRAM reduction.
CoreWeave Hits $5B Revenue, Claims AI Cloud Crown
CoreWeave announces $5B revenue milestone and claims the title of the largest AI-native cloud platform, fueled by enterprise demand and specialized infrastructure.
