cd/entity/NVIDIA Triton Inference Server· home› entities› NVIDIA Triton Inference Server

grep -l @nvidia triton inference server /news/*.json | wc -l → 1

NVIDIA Triton Inference Server

mentions 1 type Person feed RSS

// recent coverage 1 mentions

18:07

2026-07-17

netflixtechblog.medium.com

large-language-models

In-House LLM Serving at Netflix

Netflix's AI Platform team built an in-house LLM serving stack using vLLM as the paved-path inference engine, integrated with NVIDIA Triton Inference Server and a Java control plane. The platform hand…

// co-occurs with top 5 entities

Netflix 1 vLLM 1 TensorRT-LLM 1 Model Scoring Service (MSS) 1 AI Platform 1