Microsoft is not just the world’s biggest consumer of OpenAI models, but also still the largest partner providing compute, networking, and storage to OpenAI as it builds its latest GPT models. …
Microsoft Takes On Other Clouds With “Braga” Maia 200 AI Compute Engines was written by Timothy Prickett Morgan at The Next Platform.
Deploying AI applications across diverse consumer hardware has traditionally forced a trade-off. You can optimize for specific GPU configurations and achieve...Deploying AI applications across diverse consumer hardware has traditionally forced a trade-off. You can optimize for specific GPU configurations and achieve peak performance at the cost of portability. Alternatively, you can build generic, portable engines and leave performance on the table. Bridging this gap often requires manual tuning, multiple build targets, or accepting compromises.
No, we did not miss the fact that Nvidia did an “acquihire” of AI accelerator and system startup and rival Groq on Christmas Eve. …
Is Nvidia Assembling The Parts For Its Next Inference Platform? was written by Timothy Prickett Morgan at The Next Platform.
In 2025, NVIDIA partnered with Black Forest Labs (BFL) to optimize the FLUX.1 text-to-image model series, unlocking FP4 image generation performance on NVIDIA...In 2025, NVIDIA partnered with Black Forest Labs (BFL) to optimize the FLUX.1 text-to-image model series, unlocking FP4 image generation performance on NVIDIA Blackwell GeForce RTX 50 Series GPUs. As a natural extension of the latent diffusion model, FLUX.1 Kontext [dev] proved that in-context learning is a feasible technique for visual-generation models, not just large language models (LLMs).
Large language models (LLMs) and multimodal reasoning systems are rapidly expanding beyond the data center. Automotive and robotics developers increasingly want...Large language models (LLMs) and multimodal reasoning systems are rapidly expanding beyond the data center. Automotive and robotics developers increasingly want to run conversational AI agents, multimodal perception, and high-level planning directly on the vehicle or robot – where latency, reliability, and the ability to operate offline matter most. While many existing LLM and vision language…
AI‑native organizations increasingly face scaling challenges as agentic AI workflows drive context windows to millions of tokens and models scale toward...AI‑native organizations increasingly face scaling challenges as agentic AI workflows drive context windows to millions of tokens and models scale toward trillions of parameters. These systems currently rely on agentic long‑term memory for context that persists across turns, tools, and sessions so agents can build on prior reasoning instead of starting from scratch on every request.
For machine learning engineers deploying LLMs at scale, the equation is familiar and unforgiving: as context length increases, attention computation costs...For machine learning engineers deploying LLMs at scale, the equation is familiar and unforgiving: as context length increases, attention computation costs explode. Whether you’re dealing with retrieval-augmented generation (RAG) pipelines, agentic AI workflows, or long-form content generation, the complexity of attention remains a primary bottleneck. This post explains a technique known as…
As AI models get larger and architectures more complex, researchers and engineers are continuously finding new techniques to optimize the performance and...As AI models get larger and architectures more complex, researchers and engineers are continuously finding new techniques to optimize the performance and overall cost of bringing AI systems to production. Model optimization is a category of techniques focused on addressing inference service efficiency. These techniques represent the best “bang for buck” opportunities to optimize cost…
Quantization is one of the strongest levers for large-scale inference. By reducing the precision of weights, activations, and KV cache, we can reduce the memory...Quantization is one of the strongest levers for large-scale inference. By reducing the precision of weights, activations, and KV cache, we can reduce the memory footprint and compute cost—directly improving throughput, latency, and achievable context length. This blog introduces NVFP4 KV cache quantization, a new KV format that enables significant performance gains on NVIDIA Blackwell GPUs.
The NVIDIA Collective Communications Library (NCCL) provides communication APIs for low-latency and high-bandwidth collectives, enabling AI workloads to scale...The NVIDIA Collective Communications Library (NCCL) provides communication APIs for low-latency and high-bandwidth collectives, enabling AI workloads to scale from just a few GPUs on a single host to thousands of GPUs in a data center. This post discusses NCCL features that support run-time rescaling for cost optimization, as well as minimizing service downtime from faults by dynamically removing…
Large language models can solve challenging math problems. However, making them work efficiently at scale requires more than a strong checkpoint. You need the...Large language models can solve challenging math problems. However, making them work efficiently at scale requires more than a strong checkpoint. You need the right serving stack, quantization strategy, and decoding methods—often spread across different tools that don’t work together cleanly. Teams end up juggling containers, conversion scripts, and ad‑hoc glue code to compare BF16 vs FP8 or to…
Over the past few years, AI inference has evolved from single-model, single-pod deployments into complex, multicomponent systems. A model deployment may now...Over the past few years, AI inference has evolved from single-model, single-pod deployments into complex, multicomponent systems. A model deployment may now consist of several distinct components—prefill, decode, vision encoders, key value (KV) routers, and more. In addition, entire agentic pipelines are emerging, where multiple such model instances collaborate to perform reasoning, retrieval…
Login