AI Inference
NVIDIA Unveils NVFP4 for Enhanced Low-Precision AI Inference
NVIDIA introduces NVFP4, a new 4-bit floating-point format under the Blackwell architecture, aiming to optimize AI inference with improved accuracy and efficiency.
NVIDIA Dynamo Enhances Large-Scale AI Inference with llm-d Community
NVIDIA collaborates with the llm-d community to enhance open-source AI inference capabilities, leveraging its Dynamo platform for improved large-scale distributed inference.
NVIDIA Unveils TensorRT for RTX: Enhanced AI Inference on Windows 11
NVIDIA introduces TensorRT for RTX, an optimized AI inference library for Windows 11, enhancing AI experiences across creativity, gaming, and productivity apps.
NVIDIA Unveils GeForce NOW for Enhanced Game AI and Developer Access
NVIDIA's GeForce NOW expands its cloud gaming service, offering new AI tools for developers and seamless game preview experiences, broadening access for gamers globally.
NVIDIA Blackwell Sets New Standard with DeepSeek-R1 Inference Performance
NVIDIA's Blackwell GPUs achieve unprecedented DeepSeek-R1 inference performance, enhancing AI capabilities with record-breaking throughput and efficiency at NVIDIA GTC 2025.
NVIDIA Enhances AI Inference with Full-Stack Solutions
NVIDIA introduces full-stack solutions to optimize AI inference, enhancing performance, scalability, and efficiency with innovations like the Triton Inference Server and TensorRT-LLM.
AWS Expands NVIDIA NIM Microservices for Enhanced AI Inference
AWS and NVIDIA enhance AI inference capabilities by expanding NIM microservices across AWS platforms, boosting efficiency and reducing latency for generative AI applications.
NVIDIA's TensorRT-LLM Multiblock Attention Enhances AI Inference on HGX H200
NVIDIA's TensorRT-LLM introduces multiblock attention, significantly boosting AI inference throughput by up to 3.5x on the HGX H200, tackling challenges of long-sequence lengths.
Enhancing AI Inference with NVIDIA NIM and Google Kubernetes Engine
NVIDIA collaborates with Google Cloud to integrate NVIDIA NIM with Google Kubernetes Engine, offering scalable AI inference solutions through Google Cloud Marketplace.
Enhancing llama.cpp AI Inference Using CUDA Graphs
NVIDIA's integration of CUDA Graphs into llama.cpp significantly boosts AI inference performance, reducing GPU overheads and enhancing efficiency.