NVIDIA has introduced Dynamo Snapshot, a checkpoint/restore approach for AI inference workloads on Kubernetes that reduces cold-start latency from minutes to near-instantaneous startup times. The solu…
NVIDIA released CUDA 13.3 on Tuesday, marking the CUDA Python 1.0 milestone as a stable, supported release for leveraging CUDA in Python applications for AI, data science, and scientific computing. Th…
NVIDIA's Blackwell platform set a new STAC-AI benchmark record for large language model inference in financial services, outperforming prior results on the STAC-AI LANG6 test. The benchmark, developed…
FastVideo has open-sourced Dreamverse, a real-time video generation workspace that enables "vibe directing" through natural-language iteration, releasing both the frontend and backend as a reference a…
Baidu Baige has released LoongForge, an open-source training framework for large language models, vision-language models, diffusion transformers, and vision-language-action models, claiming up to 5.04…
A new GPU-accelerated Bloom filter implementation, cuSBF, achieves up to 234 times faster k-mer queries and 92 times faster insertions compared to CPU-based Super Bloom filters for DNA and protein seq…
NVIDIA researchers released Polar, a rollout framework that trains language agents through reinforcement learning without altering their agent harnesses. Using GRPO on a Qwen3.5-4B base model, Polar i…
NVIDIA released DLSS 4.5 as an Unreal Engine plugin, adding Dynamic Multi Frame Generation, a 6x mode, and a second-generation transformer model for Super Resolution. NVIDIA ACE now supports multiling…
NVIDIA has introduced the Vera CPU, positioning it as a competitive force in the AI infrastructure market. The chip is designed for AI factories, a new class of facilities that convert energy into tok…
AVTR-1, an open-weight flow-matching transformer for audio-driven avatars, has been released for real-time dialogue generation. The model renders lip-synced speech and active listening at 25 frames pe…
A developer has built an open-source agent that correlates NCCL AllReduce stalls with TCP retransmits on the same host, revealing network bottlenecks that GPU dashboards miss. The tool attaches uprobe…
ByteDance is considering capital expenditures of up to $70 billion this year to expand its AI infrastructure and data centers, according to Bloomberg, citing people familiar with the matter. Other rep…
ByteDance, the parent company of TikTok, raised its 2026 capital expenditure budget to approximately $30 billion, a 25% increase, to accelerate AI infrastructure expansion. The company plans to invest…
A team of Bayesian statisticians has developed a method to fit million-parameter models using serverless GPU computing for pennies, dramatically reducing the cost and complexity of Markov chain Monte …
Corsair Gaming announced the launch of CORSAIR PRO, a new portfolio of AI workstations and servers built on NVIDIA Grace Blackwell technology, on May 22, 2026. The company's stock rose approximately 1…
Researchers at the FlashInfer MLSYS Challenge developed a formal verification method using the SPIN model checker to detect deadlocks in CuTe DSL kernels running on NVIDIA B200 GPUs. The approach, dem…
NVIDIA's C++ template-based CUTLASS library for GPU kernels suffers from compile times of up to 20 seconds for a single kernel and over 17 minutes for full builds, prompting a shift toward Python-embe…
Newegg is offering a $750 discount on the Xidax X6 Onami Black gaming PC, bringing the price to $6,249.99, and including a free 007 First Light game bundle. The prebuilt system features an RTX 5090 gr…
Taiwan Semiconductor Manufacturing Company (TSMC) plans to raise prices on its 3nm process node by 15% in the second half of 2026, driven by surging demand from AI and high-performance computing clien…
0G Labs, in partnership with China Mobile, successfully trained a 107-billion-parameter AI model using its DiLoCoX framework, marking the first decentralized training of a model exceeding 100 billion …