<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Tensorrt-Llm on Zhanyl Abdybaeva</title>
    <link>https://zhanyl-tech.github.io/tags/tensorrt-llm/</link>
    <description>Recent content in Tensorrt-Llm on Zhanyl Abdybaeva</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 20 Jan 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://zhanyl-tech.github.io/tags/tensorrt-llm/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>vLLM vs TensorRT-LLM: First Throughput Numbers on Llama-3 70B</title>
      <link>https://zhanyl-tech.github.io/experiments/2026-01-20-vllm-vs-tensorrt-llm-first-look/</link>
      <pubDate>Tue, 20 Jan 2026 00:00:00 +0000</pubDate>
      <guid>https://zhanyl-tech.github.io/experiments/2026-01-20-vllm-vs-tensorrt-llm-first-look/</guid>
      <description>Quick benchmark comparing vLLM and TensorRT-LLM throughput on a single A100 80GB with Llama-3 70B. Setup notes, raw numbers, and what I&amp;#39;d investigate next.</description>
    </item>
  </channel>
</rss>
