<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: simoiacos</title><link>https://news.ycombinator.com/user?id=simoiacos</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 04 Oct 2026 06:10:29 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=simoiacos" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by simoiacos in "From the creator of Redis; run LLM locally with ds4"]]></title><description><![CDATA[
<p>Thank you, appreciate it!</p>
]]></description><pubDate>Sat, 03 Oct 2026 21:14:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=49947844</link><dc:creator>simoiacos</dc:creator><comments>https://news.ycombinator.com/item?id=49947844</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49947844</guid></item><item><title><![CDATA[New comment by simoiacos in "From the creator of Redis; run LLM locally with ds4"]]></title><description><![CDATA[
<p>I just added experimental support for Xe-LPG and Xe-LPG+ in main so you should be able to try it without a patch now.<p>As I said, I don't have the hardware to test it myself, so let me know how it goes!</p>
]]></description><pubDate>Sat, 03 Oct 2026 14:38:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=49944681</link><dc:creator>simoiacos</dc:creator><comments>https://news.ycombinator.com/item?id=49944681</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49944681</guid></item><item><title><![CDATA[New comment by simoiacos in "From the creator of Redis; run LLM locally with ds4"]]></title><description><![CDATA[
<p>Please open a PR! I was too conservative with the supported devices.<p>If your GPU supports XMX we could also explore using it to improve the prefill kernel, but I don't have the hardware to test it myself.</p>
]]></description><pubDate>Fri, 02 Oct 2026 23:13:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=49939732</link><dc:creator>simoiacos</dc:creator><comments>https://news.ycombinator.com/item?id=49939732</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49939732</guid></item><item><title><![CDATA[New comment by simoiacos in "From the creator of Redis; run LLM locally with ds4"]]></title><description><![CDATA[
<p>He recently said that he finds Rust less ergonomic and that this also affects code written by LLMs, which he thinks excel at writing C partly because of the enormous, high-quality codebase they were trained on. He sees security-critical code as a reason to choose Rust.<p>The video is in Italian but has an auto-dubbed English audio track:
<a href="https://www.youtube.com/watch?v=sOt0WpQG5eU\&t=526s" rel="nofollow">https://www.youtube.com/watch?v=sOt0WpQG5eU\&t=526s</a></p>
]]></description><pubDate>Fri, 02 Oct 2026 22:49:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=49939565</link><dc:creator>simoiacos</dc:creator><comments>https://news.ycombinator.com/item?id=49939565</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49939565</guid></item><item><title><![CDATA[New comment by simoiacos in "From the creator of Redis; run LLM locally with ds4"]]></title><description><![CDATA[
<p>Yeah I see the value but I built Xenolith to target smaller models.<p>I heard antirez saying that he designed DwarfStar also to be forked and tuned to everyone's specific needs. Do you have a specific machine/spec in mind?</p>
]]></description><pubDate>Fri, 02 Oct 2026 22:15:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=49939292</link><dc:creator>simoiacos</dc:creator><comments>https://news.ycombinator.com/item?id=49939292</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49939292</guid></item><item><title><![CDATA[New comment by simoiacos in "From the creator of Redis; run LLM locally with ds4"]]></title><description><![CDATA[
<p>Nothing comparable but inspired from DwarfStar I wrote a little inference engine for Intel Xe-LP (no XMX) 32GB laptops. The only model supported right now is a quantized Gemma-4, but I don't exclude in the future to support other MoE of similar size. Too bad we have no Qwen 3.8 35B-A3B yet.<p>I'm also looking into expanding the protocol and the engine to support various steering techniques.<p><a href="https://github.com/simoneiacomino/xenolith" rel="nofollow">https://github.com/simoneiacomino/xenolith</a></p>
]]></description><pubDate>Fri, 02 Oct 2026 20:15:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=49938078</link><dc:creator>simoiacos</dc:creator><comments>https://news.ycombinator.com/item?id=49938078</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49938078</guid></item><item><title><![CDATA[New comment by simoiacos in "Ask HN: What are you working on? (January 2026)"]]></title><description><![CDATA[
<p>Really cute game, nice work!</p>
]]></description><pubDate>Sun, 11 Jan 2026 18:35:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=46578318</link><dc:creator>simoiacos</dc:creator><comments>https://news.ycombinator.com/item?id=46578318</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46578318</guid></item></channel></rss>