ProductAI Software / Framework

TensorRT-LLM

NVIDIA library for optimizing and serving large language models on its GPUs.

Made by NVIDIA

Covered in 1 article · April 2026

Mentioned in

Apr 7, 2026

AIFlatAttention Claims 4× Speedup Over FlashAttention-3 — But on What Hardware?

Covered alongsideCerebras Cerebras WSE-3 ClusterFusion DeepSeek-v3 FlashAttention-2 FlashAttention-3

More from NVIDIA

BerzeliusSupercomputer CUDA-QQuantum Software CUDA-Q QECQuantum Software CUDAQ-RealtimeQuantum Software Feynman GPU ArchitectureGPU GPUDirect RDMAInterconnect GraspGenRobotics System Isaac GR00T N1.6AI Model Isaac LabSimulation Software NCCLAI Software / Framework NCCL EPAI Software / Framework NIXL-EPAI Software / Framework