NVIDIA releases TensorRT-LLM
TensorRT-LLM released
Why it matters
Integrated in-flight batching, paged attention and FP8 into the vendor stack
Source — Primary sources first; secondary reports are labelled “Press”
Officialdeveloper.nvidia.comhttps://developer.nvidia.com/blog/optimizing-inference-on-llms-with-tensorrt-llm-now-publicly-available/Added in Week 35, 2026 · See that week