<?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>FP8 on Learn by Tanhdev</title><link>https://learn.tanhdev.com/tags/fp8/</link><description>Recent content in FP8 on Learn by Tanhdev</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 17 May 2026 12:00:00 +0700</lastBuildDate><atom:link href="https://learn.tanhdev.com/tags/fp8/index.xml" rel="self" type="application/rss+xml"/><item><title>Tối Ưu Hóa Inference &amp; Triển Khai vLLM Trên Production</title><link>https://learn.tanhdev.com/series/ai-data-engineering-pipeline/part-8-inference-optimization-vllm/</link><pubDate>Sun, 17 May 2026 12:00:00 +0700</pubDate><guid>https://learn.tanhdev.com/series/ai-data-engineering-pipeline/part-8-inference-optimization-vllm/</guid><description>Vượt qua giới hạn VRAM và tối ưu chi phí Server khi triển khai LLM 70B với vLLM, PagedAttention và Quantization FP8/AWQ.</description></item></channel></rss>