---
title: "#tensorrt articles | Hashnode"
description: "Explore 7 articles tagged #tensorrt on Hashnode. Tutorials, guides, and how-tos from the community."
url: "https://hashnode.com/tag/tensorrt"
---

Tag

# #tensorrt

7 posts · 0 followers

[Jakson Tate](https://hashnode.com/@jakson-tate) · [Nov 6](https://hashnode.com/posts/deploying-tensorrt-llm-bare-metal/6aed91451054b27567c89d32)

### [TensorRT-LLM Production Deployment: FP8, NVFP4, MoE & Disaggregated Serving](https://servermo.hashnode.dev/deploying-tensorrt-llm-bare-metal?utm_source=hashnode&utm_medium=feed)

An SRE blueprint for PyTorch backend selection, quantization, MoE parallelism, NIXL disaggregated serving, and bare-metal GPU infrastructure.

8 min read · [servermo.hashnode.dev](https://servermo.hashnode.dev/deploying-tensorrt-llm-bare-metal?utm_source=hashnode&utm_medium=feed)

[Khadim Hussain](https://hashnode.com/@khadimxai) · [Oct 23](https://hashnode.com/posts/tensorrt-int8-vs-fp16-on-rf-detr-measured-on-an-rtx-5090/6adbccf2d53c4a369c38ed3c)

### [TensorRT INT8 vs FP16 on RF-DETR, Measured on an RTX 5090](https://khadimhussain0.hashnode.dev/tensorrt-int8-vs-fp16-on-rf-detr-measured-on-an-rtx-5090?utm_source=hashnode&utm_medium=feed)

A calibrated TensorRT INT8 build of RF-DETR put 0 layers in INT8 on an RTX 5090. Measured INT8, FP16, CPU quantization and distillation side by side.

11 min read · [khadimhussain0.hashnode.dev](https://khadimhussain0.hashnode.dev/tensorrt-int8-vs-fp16-on-rf-detr-measured-on-an-rtx-5090?utm_source=hashnode&utm_medium=feed)

[aikic0der](https://hashnode.com/@nguyenqh) · [Nov 18, 2024](https://hashnode.com/posts/triton-response-cache-for-tensorrt-models/673b5c973fc5ecc596594230)

### [Triton Response Cache for TensorRT models](https://nguyenqh.hashnode.dev/triton-response-cache-for-tensorrt-models?utm_source=hashnode&utm_medium=feed)

Introduction Triton Response Cache Triton Response Cache (referred to as the Cache from now on) is a feature of NVIDIA’s Triton Inference Server that stores the response of a model inference request so that if the same request comes in again, the ser...

4 min read · [nguyenqh.hashnode.dev](https://nguyenqh.hashnode.dev/triton-response-cache-for-tensorrt-models?utm_source=hashnode&utm_medium=feed)

[Winston Liu](https://hashnode.com/@greybird) · [Apr 18, 2024](https://hashnode.com/posts/some-notes-about-nvidia-tensorrt/6620e7efd580548f86152fa0)

### [Some Notes About NVIDIA TensorRT](https://greybird.hashnode.dev/some-notes-about-nvidia-tensorrt?utm_source=hashnode&utm_medium=feed)

Although I have been using TensorRT framework for a few months, but I haven't get a systematically understanding of its whole view. So, it's here, and I am going to note some facts about this fantastic machine learning inference tool. What is TensorR...

3 min read · [greybird.hashnode.dev](https://greybird.hashnode.dev/some-notes-about-nvidia-tensorrt?utm_source=hashnode&utm_medium=feed)