Artificial IndexHumanity's AI Index
Artificial Index record

TensorRT-LLM

NVIDIA open-source library for optimizing and serving large language-model inference on NVIDIA GPUs.

OrganizationNVIDIA
StatusPublic / developer
APIYes / platform APIs
LifecycleActive
Catalog profileAvailable
Index completeness38%
Models indexed0
Sources2

Use profile

Building, hosting, evaluating, serving or operating AI applications and models.

Limitations / notes

Available models, regions, quotas, prices and enterprise controls change over time.

FrameworkInferenceOpen Source

Public references

Primary public sourcehttps://github.com/NVIDIA/TensorRT-LLMOpen ↗Documentation / referencehttps://nvidia.github.io/TensorRT-LLM/Docs ↗
Verification: Official public source linked; deeper field-level audit pending
Loading lineage…
Loading company positioning and measured evidence…
Loading benchmark & performance evidence…
Loading AI metrics…
Loading research profile…

Recent news & updates

Official product/model updates are shown separately from recent external coverage so news discovery does not silently become verified Artificial Index data.
loading news…
Loading recent updates and coverage…

Related systems