<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" ><generator uri="https://jekyllrb.com/" version="3.10.0">Jekyll</generator><link href="https://itayhubara.github.io/feed.xml" rel="self" type="application/atom+xml" /><link href="https://itayhubara.github.io/" rel="alternate" type="text/html" /><updated>2026-01-09T04:37:16-08:00</updated><id>https://itayhubara.github.io/feed.xml</id><title type="html">Itay Hubara / PhD</title><subtitle>Techion Alumnai; MLPerf member; Director of AI at a Stealth Mode Startup.</subtitle><author><name>Itay Hubara</name></author><entry><title type="html">Mlperf Inference SDXL Benchmark</title><link href="https://itayhubara.github.io/posts/2024/08/blog-post-3/" rel="alternate" type="text/html" title="Mlperf Inference SDXL Benchmark" /><published>2024-08-27T00:00:00-07:00</published><updated>2024-08-27T00:00:00-07:00</updated><id>https://itayhubara.github.io/posts/2024/08/blog-post-3</id><content type="html" xml:base="https://itayhubara.github.io/posts/2024/08/blog-post-3/"><![CDATA[<p>This is a technical blog on the MLPerf SDXL inference benchmark. <a href="https://mlcommons.org/2024/03/mlperf-llama2-70b/">BLOG</a></p>]]></content><author><name>Itay Hubara</name></author><category term="Inference" /><category term="MLPerf" /><summary type="html"><![CDATA[This is a technical blog on the MLPerf SDXL inference benchmark. BLOG]]></summary></entry><entry><title type="html">Mlperf Inference llama2-70b benchmark’</title><link href="https://itayhubara.github.io/posts/2012/08/blog-post-1/" rel="alternate" type="text/html" title="Mlperf Inference llama2-70b benchmark’" /><published>2024-03-27T00:00:00-07:00</published><updated>2024-03-27T00:00:00-07:00</updated><id>https://itayhubara.github.io/posts/2012/08/blog-post-1</id><content type="html" xml:base="https://itayhubara.github.io/posts/2012/08/blog-post-1/"><![CDATA[<p>This is a technical blog on the MLPerf inference bemchmark. <a href="https://mlcommons.org/2024/03/mlperf-llama2-70b/">BLOG</a></p>]]></content><author><name>Itay Hubara</name></author><category term="Inference" /><category term="MLPerf" /><summary type="html"><![CDATA[This is a technical blog on the MLPerf inference bemchmark. BLOG]]></summary></entry><entry><title type="html">Data packing for MLPerf BERT</title><link href="https://itayhubara.github.io/posts/2013/08/blog-post-2/" rel="alternate" type="text/html" title="Data packing for MLPerf BERT" /><published>2021-08-14T00:00:00-07:00</published><updated>2021-08-14T00:00:00-07:00</updated><id>https://itayhubara.github.io/posts/2013/08/blog-post-2</id><content type="html" xml:base="https://itayhubara.github.io/posts/2013/08/blog-post-2/"><![CDATA[<p>This is a technical blog about data packing for training acceleration of encoder models <a href="https://developer.habana.ai/tutorials/tensorflow/data-packing-process-for-mlperf-bert/">BLOG</a></p>]]></content><author><name>Itay Hubara</name></author><category term="cool posts" /><category term="category1" /><category term="category2" /><summary type="html"><![CDATA[This is a technical blog about data packing for training acceleration of encoder models BLOG]]></summary></entry></feed>