<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Lizard inference engineering: Two native providers should remain explicit]]></title><description><![CDATA[<p dir="auto"><strong>Inference Engineering · Day 18 · Morning</strong></p>
<p dir="auto"><img src="https://lizard-llm.qendryx.com/diagrams/two-engines-decision.png" alt="Two native providers should remain explicit editorial visual — lizard-llm.qendryx.com" class=" img-fluid img-markdown" /></p>
<p dir="auto">A provider selector is meaningless if the runtime silently launches a different engine.</p>
<p dir="auto">Lizard carries the requested provider through server launch, health checks, benchmark artifacts, onboarding activation, and Chat telemetry. A mismatch is treated as an error rather than a successful run under the wrong label.</p>
<p dir="auto">Provider identity belongs in both execution and evidence.</p>
<p dir="auto">Can you prove which engine served the last response in your local stack?</p>
<p dir="auto"><strong>Engineering fact:</strong> Lizard exposes lizard-native and Caterpillar as separate runtime providers in serve, onboarding, benchmark, and Chat paths instead of silently substituting one for the other.</p>
<p dir="auto"><a href="https://lizard-llm.qendryx.com/docs.html#caterpillar" rel="nofollow ugc">Read the relevant Lizard page</a></p>
<p dir="auto">#Caterpillar #LizardLLM #GPUProgramming #LocalAI #GGUF</p>
<p dir="auto">&lt;!-- lizard-marketing-slot:day-18-am --&gt;</p>
]]></description><link>https://community.lizard-llm.qendryx.com/topic/75/lizard-inference-engineering-two-native-providers-should-remain-explicit</link><generator>RSS for Node</generator><lastBuildDate>Mon, 24 Aug 2026 01:37:03 GMT</lastBuildDate><atom:link href="https://community.lizard-llm.qendryx.com/topic/75.rss" rel="self" type="application/rss+xml"/><pubDate>Mon, 10 Aug 2026 01:00:12 GMT</pubDate><ttl>60</ttl></channel></rss>