636
75
... government of the people, by the people, for the people ... — Abraham Lincoln, Gettysburg Address (1863) The cost of AI is dropping rapidly. GPT-4-class capabilities cost roughly 30 per million tokens in early 2023; today the same runs under 1 , and some providers are pushing costs below $0.10 . Across benchmarks, inference prices have fallen between 9x…
Congratulations to the Berkeley Artificial Intelligence Research (BAIR) Lab class of 2026! This year, BAIR celebrates another remarkable group of Ph.D. graduates whose curiosity, creativity, and perseverance have pushed the frontiers of artificial intelligence and machine learning. Their work spans the breadth of modern AI — robotics and embodied intelligence, large language models and reasoning, computer vision, generative modeling, AI…
Life sciences has entered an era of computational scale, and for more than a decade, NVIDIA has built the full GPU-accelerated computing stack — spanning hardware, frameworks, libraries, models, microservices and domain-specific tools — to help researchers run more sophisticated workflows and iterate faster. This week, Anthropic announced Claude Science, an AI workbench for science […]
OpenAI and Broadcom introduce Jalapeño, a custom AI chip built for LLM inference to improve performance, efficiency, and scale across AI systems.
ParallelKernelBench tests whether LLMs can write fast multi-GPU CUDA kernels across 87 real workloads. The best model solves under a third, but a few generated kernels beat any public implementation.
Together AI built the fastest speech-to-text stack on Artificial Analysis by treating ASR as a full-path systems problem, not just a GPU inference problem.
Overview of adaptive parallel reasoning. What if a reasoning model could decide for itself when to decompose and parallelize independent subtasks, how many concurrent threads to spawn, and how to coordinate them based on the problem at hand? We provide a detailed analysis of recent progress in the field of parallel reasoning, especially Adaptive Parallel Reasoning. Disclosure: this post is…
Learn how to deploy any Hugging Face model in one session using Goose and Together's Dedicated Container Inference. Skip the setup complexity — one prompt gets your model running in a production-grade GPU environment on release day.
Learn how AI-native companies design multi-tenant GPU clusters that pool capacity without sacrificing team isolation — and how Together AI makes it work in practice.
The team behind FlashAttention and ThunderKittens — how Together AI's kernel researchers close the gap between GPU hardware and production AI.
Together GPU Clusters now include built-in autoscaling, RBAC, full-stack observability, and self-healing node repair—giving teams production-ready GPU infrastructure that scales efficiently, stays resilient, and supports shared enterprise workloads.
As GPU throughput outpaces memory bandwidth, kernels must evolve. We introduce FlashAttention-4, featuring new pipelining for maximum overlap, 2-CTA MMA modes to reduce shared memory traffic, and a hardware-software hybrid approach to softmax exponentials.
Learn how to reduce inference latency without massive cost using proven inference optimization tactics — improving throughput, GPU utilization, and cost efficiency while balancing throughput vs. latency tradeoffs.
The artificial intelligence coding revolution comes with a catch: it's expensive. Claude Code , Anthropic's terminal-based AI agent that can write, debug, and deploy code…
Learn how foundation models are trained at scale using multi-node GPU clusters, including distributed training techniques, infrastructure requirements, and practical steps to scale training efficiently.
Nous Research , the open-source artificial intelligence startup backed by crypto venture firm Paradigm , released a new competitive programming model on Monday that it…
Dan Fu, our VP of Kernels, has published a new post challenging the idea that AI is hitting a hardware wall. He argues that we are vastly underutilizing current chips and that better software-hardware co-design will unlock the next order of magnitude in performance.
Together AI achieves up to 2x faster inference for top open-source models like Qwen, DeepSeek, and Kimi through GPU optimization, advanced speculative decoding, and FP4 quantization—ranking #1 in speed benchmarks on NVIDIA Blackwell architecture.
Samsung and SK join OpenAI’s Stargate initiative to expand global AI infrastructure, scaling advanced memory chip production and building next-gen data centers in Korea.
Ollama now includes a significantly improved model scheduling system, reducing crashes due to out of memory issues, maximizing GPU utilization and performance, especially on multi-GPU systems.
