<?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>Token-Count-Based on Tenu Tech Brief</title>
    <link>https://cluster-site.onrender.com/tags/token-count-based/</link>
    <description>Recent content in Token-Count-Based on Tenu Tech Brief</description>
    <generator>Hugo -- 0.146.0</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 24 Feb 2026 06:03:02 +0000</lastBuildDate>
    <atom:link href="https://cluster-site.onrender.com/tags/token-count-based/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Token-count-based Batching: Faster, Cheaper Embedding Inference for Queries</title>
      <link>https://cluster-site.onrender.com/posts/token-count-based-batching-faster-cheaper-embedding-inference-for-queries/</link>
      <pubDate>Thu, 18 Dec 2025 15:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/token-count-based-batching-faster-cheaper-embedding-inference-for-queries/</guid>
      <description>• Token-count-based Batching: Faster, Cheaper Embedding Inference for Queries Embedding model inference often struggles with efficiency when serving large volumes of short requests</description>
    </item>
  </channel>
</rss>
