<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: jtatarchuk</title><link>https://news.ycombinator.com/user?id=jtatarchuk</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 09 Sep 2026 09:11:36 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=jtatarchuk" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by jtatarchuk in "Ask HN: Why hasn’t AMD made a viable CUDA alternative?"]]></title><description><![CDATA[
<p>Ya'll should have come to Beyond CUDA.<p><a href="https://www.linkedin.com/posts/jtatarchuk_beyondcuda-democratizecompute-thefutureisopen-activity-7312527320743907330-NDkp?utm_source=share&utm_medium=member_desktop&rcm=ACoAAAtWOS4BaMaYiX7S5F24HG_eBOc4OsXef9k" rel="nofollow">https://www.linkedin.com/posts/jtatarchuk_beyondcuda-democra...</a></p>
]]></description><pubDate>Tue, 01 Apr 2025 21:13:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=43551422</link><dc:creator>jtatarchuk</dc:creator><comments>https://news.ycombinator.com/item?id=43551422</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43551422</guid></item><item><title><![CDATA[Attention is NOT all you need: Qwerky-72B trained using only 8 AMD MI300X GPUs]]></title><description><![CDATA[
<p>Article URL: <a href="https://substack.recursal.ai/p/qwerky-72b-and-32b-training-large">https://substack.recursal.ai/p/qwerky-72b-and-32b-training-large</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43550538">https://news.ycombinator.com/item?id=43550538</a></p>
<p>Points: 20</p>
<p># Comments: 3</p>
]]></description><pubDate>Tue, 01 Apr 2025 19:31:46 +0000</pubDate><link>https://substack.recursal.ai/p/qwerky-72b-and-32b-training-large</link><dc:creator>jtatarchuk</dc:creator><comments>https://news.ycombinator.com/item?id=43550538</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43550538</guid></item><item><title><![CDATA[TensorWave and MK1 partner to unlock fast inference on AMD]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.morningstar.com/news/business-wire/20240521368988/tensorwave-partners-with-neuralink-engineers-new-startup-mk1-to-bring-lightning-fast-ai-inference-to-amd-cloud">https://www.morningstar.com/news/business-wire/20240521368988/tensorwave-partners-with-neuralink-engineers-new-startup-mk1-to-bring-lightning-fast-ai-inference-to-amd-cloud</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=40442506">https://news.ycombinator.com/item?id=40442506</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 22 May 2024 15:56:44 +0000</pubDate><link>https://www.morningstar.com/news/business-wire/20240521368988/tensorwave-partners-with-neuralink-engineers-new-startup-mk1-to-bring-lightning-fast-ai-inference-to-amd-cloud</link><dc:creator>jtatarchuk</dc:creator><comments>https://news.ycombinator.com/item?id=40442506</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40442506</guid></item><item><title><![CDATA[New comment by jtatarchuk in "Take AMD MI300X for a test drive"]]></title><description><![CDATA[
<p>Free to try it out and then $1/hr to reserve it.</p>
]]></description><pubDate>Tue, 02 Apr 2024 16:52:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=39907958</link><dc:creator>jtatarchuk</dc:creator><comments>https://news.ycombinator.com/item?id=39907958</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39907958</guid></item><item><title><![CDATA[New comment by jtatarchuk in "Take AMD MI300X for a test drive"]]></title><description><![CDATA[
<p>Need compute? Try it free. Limited time $1/hr for the first 3 months.<p>AMD MI300X vs H100
2.4X Higher Memory Capacity
1.6X Higher Memory Bandwidth
1.3X FP8 TFLOPS
1.3X FP16 TFLOPS<p>Up To 20% Faster Vs H100 (Llama 2 70B) In 1v1 Comparison
Up To 20% Faster Vs H100 (FlashAttention 2) in 1v1 Comparison
Up To 40% Faster Vs H100 (Llama 2 70B) in 8v8 Server
Up To 60% Faster Vs H100 (Bloom 176B) In 8v8 Server<p>TensorWave</p>
]]></description><pubDate>Tue, 02 Apr 2024 15:54:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=39907198</link><dc:creator>jtatarchuk</dc:creator><comments>https://news.ycombinator.com/item?id=39907198</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39907198</guid></item><item><title><![CDATA[Take AMD MI300X for a test drive]]></title><description><![CDATA[
<p>Article URL: <a href="https://tensorwave.com/">https://tensorwave.com/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=39907197">https://news.ycombinator.com/item?id=39907197</a></p>
<p>Points: 3</p>
<p># Comments: 3</p>
]]></description><pubDate>Tue, 02 Apr 2024 15:54:18 +0000</pubDate><link>https://tensorwave.com/</link><dc:creator>jtatarchuk</dc:creator><comments>https://news.ycombinator.com/item?id=39907197</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39907197</guid></item><item><title><![CDATA[New comment by jtatarchuk in "I Am Sam Altman, President of Y Combinator.  AMA"]]></title><description><![CDATA[
<p>My cofounders and I believe CRM is broken... With a heavy emphasis on management and not the customer... What other areas of CRM do you see need improving?</p>
]]></description><pubDate>Sat, 19 Mar 2016 02:30:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=11316961</link><dc:creator>jtatarchuk</dc:creator><comments>https://news.ycombinator.com/item?id=11316961</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=11316961</guid></item></channel></rss>