<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Gpu on jonam'Log</title><link>https://www.jonam.io/tags/gpu/</link><description>Recent content in Gpu on jonam'Log</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>&amp;copy; 2026 Manoj. All Rights Reserved.</copyright><lastBuildDate>Mon, 18 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.jonam.io/tags/gpu/index.xml" rel="self" type="application/rss+xml"/><item><title>InferGrid</title><link>https://www.jonam.io/journal/inference-engineering/product-ideas/infergrid/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://www.jonam.io/journal/inference-engineering/product-ideas/infergrid/</guid><description>Measure why your GPU bill is high, then tune batching, speculation, and quantization automatically.</description></item><item><title>Roofline-Adaptive Inference Scheduler</title><link>https://www.jonam.io/journal/inference-engineering/research-topics/roofline-adaptive-inference-scheduler/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://www.jonam.io/journal/inference-engineering/research-topics/roofline-adaptive-inference-scheduler/</guid><description>Move from static max_num_seqs to a feedback loop that chases the hardware ridge point.</description></item><item><title>DraftOS</title><link>https://www.jonam.io/journal/inference-engineering/product-ideas/draftos/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://www.jonam.io/journal/inference-engineering/product-ideas/draftos/</guid><description>Use idle CPU cores on GPU instances to draft tokens while the GPU verifies.</description></item></channel></rss>