<?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" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by saniya jaswani on Medium]]></title>
        <description><![CDATA[Stories by saniya jaswani on Medium]]></description>
        <link>https://medium.com/@saniyajaswani12?source=rss-23cc3547570------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*HwV70EpVtEPvQqkTKb65jg.jpeg</url>
            <title>Stories by saniya jaswani on Medium</title>
            <link>https://medium.com/@saniyajaswani12?source=rss-23cc3547570------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sun, 22 Nov 2026 01:46:53 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@saniyajaswani12/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[If Your Model Inference is Slow, MOE Can Fix it]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/if-your-model-inference-is-slow-moe-can-fix-it-862635da82d3?source=rss-23cc3547570------2"><img src="https://cdn-images-1.medium.com/max/1944/1*_pwtOVI7bMHZGPoEdDCVyQ.png" width="1944"></a></p><p class="medium-feed-snippet">&#x201C;Mixture of Experts makes model inference faster. To scale request volume, MoE optimizes token routing.&#x201D;</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/if-your-model-inference-is-slow-moe-can-fix-it-862635da82d3?source=rss-23cc3547570------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/if-your-model-inference-is-slow-moe-can-fix-it-862635da82d3?source=rss-23cc3547570------2</link>
            <guid isPermaLink="false">https://medium.com/p/862635da82d3</guid>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[llm]]></category>
            <dc:creator><![CDATA[saniya jaswani]]></dc:creator>
            <pubDate>Tue, 16 Jun 2026 23:01:01 GMT</pubDate>
            <atom:updated>2026-06-16T23:01:01.046Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Which RAG Works for You in Production?]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/which-rag-works-for-you-in-production-344b5c3d7921?source=rss-23cc3547570------2"><img src="https://cdn-images-1.medium.com/max/1920/1*XM_f723z0z956ROkuiVmOA.jpeg" width="1920"></a></p><p class="medium-feed-snippet">A guide to naive RAG, advanced retrieval strategies, Flare-RAG, GraphRAG, and agentic pipelines, and how to create your architecture.</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/which-rag-works-for-you-in-production-344b5c3d7921?source=rss-23cc3547570------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/which-rag-works-for-you-in-production-344b5c3d7921?source=rss-23cc3547570------2</link>
            <guid isPermaLink="false">https://medium.com/p/344b5c3d7921</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[deep-learning]]></category>
            <dc:creator><![CDATA[saniya jaswani]]></dc:creator>
            <pubDate>Sat, 23 May 2026 17:31:00 GMT</pubDate>
            <atom:updated>2026-05-23T17:31:00.605Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[4 Memory Types that Your Agent Must Have]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/4-memory-types-that-your-agent-must-have-cab1b8daa186?source=rss-23cc3547570------2"><img src="https://cdn-images-1.medium.com/max/1920/1*ylrQVEI0nypW3N9IlknMtA.png" width="1920"></a></p><p class="medium-feed-snippet">If you do not design your agent like this, it will fail in production.</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/4-memory-types-that-your-agent-must-have-cab1b8daa186?source=rss-23cc3547570------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/4-memory-types-that-your-agent-must-have-cab1b8daa186?source=rss-23cc3547570------2</link>
            <guid isPermaLink="false">https://medium.com/p/cab1b8daa186</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[ai]]></category>
            <dc:creator><![CDATA[saniya jaswani]]></dc:creator>
            <pubDate>Thu, 21 May 2026 21:01:00 GMT</pubDate>
            <atom:updated>2026-05-21T21:01:00.813Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[LLM Inference: From Theory to Cost Effective Deployment]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@saniyajaswani12/llm-inference-from-theory-to-cost-effective-deployment-851486d6d483?source=rss-23cc3547570------2"><img src="https://cdn-images-1.medium.com/max/850/1*7PWesBuX2ht4ajyFTNKdag.jpeg" width="850"></a></p><p class="medium-feed-snippet">LLM inference is not normal deep learning model deployment nor is it trivial when it comes to managing scale, performance and COST&#x2026;</p><p class="medium-feed-link"><a href="https://medium.com/@saniyajaswani12/llm-inference-from-theory-to-cost-effective-deployment-851486d6d483?source=rss-23cc3547570------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@saniyajaswani12/llm-inference-from-theory-to-cost-effective-deployment-851486d6d483?source=rss-23cc3547570------2</link>
            <guid isPermaLink="false">https://medium.com/p/851486d6d483</guid>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[machine-learning]]></category>
            <dc:creator><![CDATA[saniya jaswani]]></dc:creator>
            <pubDate>Thu, 05 Mar 2026 02:01:22 GMT</pubDate>
            <atom:updated>2026-03-05T02:01:22.035Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[What did Deepseek-R1 did new?]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@saniyajaswani12/what-did-deepseek-r1-did-new-6e1fd0cc84b4?source=rss-23cc3547570------2"><img src="https://cdn-images-1.medium.com/max/1660/1*pi9Z0FmdnVewEPuQJoTYUQ.png" width="1660"></a></p><p class="medium-feed-snippet">How did this paper win over GPT 4 ?</p><p class="medium-feed-link"><a href="https://medium.com/@saniyajaswani12/what-did-deepseek-r1-did-new-6e1fd0cc84b4?source=rss-23cc3547570------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@saniyajaswani12/what-did-deepseek-r1-did-new-6e1fd0cc84b4?source=rss-23cc3547570------2</link>
            <guid isPermaLink="false">https://medium.com/p/6e1fd0cc84b4</guid>
            <category><![CDATA[reinforcement-learning]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[ai-agent]]></category>
            <dc:creator><![CDATA[saniya jaswani]]></dc:creator>
            <pubDate>Sun, 15 Feb 2026 16:01:00 GMT</pubDate>
            <atom:updated>2026-02-15T16:01:00.789Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[How to scale your LLM training — Last part]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-last-part-75a5438b9950?source=rss-23cc3547570------2"><img src="https://cdn-images-1.medium.com/max/1070/1*nErjWfxpaEIg5DqXzjPRGA.jpeg" width="1070"></a></p><p class="medium-feed-snippet">Taking 70B Model, what GPU would i choose and what would be my batch size.</p><p class="medium-feed-link"><a href="https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-last-part-75a5438b9950?source=rss-23cc3547570------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-last-part-75a5438b9950?source=rss-23cc3547570------2</link>
            <guid isPermaLink="false">https://medium.com/p/75a5438b9950</guid>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[llm]]></category>
            <dc:creator><![CDATA[saniya jaswani]]></dc:creator>
            <pubDate>Sat, 14 Feb 2026 16:01:01 GMT</pubDate>
            <atom:updated>2026-02-14T16:01:01.402Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[How to scale your LLM training — Part 4]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-part-4-1d70ad04e61b?source=rss-23cc3547570------2"><img src="https://cdn-images-1.medium.com/max/2600/1*-vyRPAl0B6ESvgXCaE70rA.jpeg" width="5184"></a></p><p class="medium-feed-snippet">Cool stuff about, what would technique you would be doing for training.</p><p class="medium-feed-link"><a href="https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-part-4-1d70ad04e61b?source=rss-23cc3547570------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-part-4-1d70ad04e61b?source=rss-23cc3547570------2</link>
            <guid isPermaLink="false">https://medium.com/p/1d70ad04e61b</guid>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[reinforcement-learning]]></category>
            <category><![CDATA[ai-agent]]></category>
            <dc:creator><![CDATA[saniya jaswani]]></dc:creator>
            <pubDate>Fri, 13 Feb 2026 23:29:21 GMT</pubDate>
            <atom:updated>2026-02-13T23:29:21.223Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[How to scale your LLM training — Part 3]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-part-3-9b67d23b4db6?source=rss-23cc3547570------2"><img src="https://cdn-images-1.medium.com/max/1036/1*HmHwP93j8ldCKg-Ml0OO4A.png" width="1036"></a></p><p class="medium-feed-snippet">Estimate exactly how much time would take to complete training given Parameter and Database size</p><p class="medium-feed-link"><a href="https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-part-3-9b67d23b4db6?source=rss-23cc3547570------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-part-3-9b67d23b4db6?source=rss-23cc3547570------2</link>
            <guid isPermaLink="false">https://medium.com/p/9b67d23b4db6</guid>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[chatgpt]]></category>
            <dc:creator><![CDATA[saniya jaswani]]></dc:creator>
            <pubDate>Thu, 12 Feb 2026 03:57:16 GMT</pubDate>
            <atom:updated>2026-02-12T03:57:16.287Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[How to scale your LLM training — Part 2]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-part-2-85d04b3c28f3?source=rss-23cc3547570------2"><img src="https://cdn-images-1.medium.com/max/1246/1*CjNGPB2BiLa03z0zpCIhyg.png" width="1246"></a></p><p class="medium-feed-snippet">Structure of TPU &amp; how does data move in TPU</p><p class="medium-feed-link"><a href="https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-part-2-85d04b3c28f3?source=rss-23cc3547570------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-part-2-85d04b3c28f3?source=rss-23cc3547570------2</link>
            <guid isPermaLink="false">https://medium.com/p/85d04b3c28f3</guid>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[reinforcement-learning]]></category>
            <dc:creator><![CDATA[saniya jaswani]]></dc:creator>
            <pubDate>Wed, 11 Feb 2026 16:01:07 GMT</pubDate>
            <atom:updated>2026-02-11T16:01:07.964Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[How to scale your LLM training]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-b7ccaeb848a8?source=rss-23cc3547570------2"><img src="https://cdn-images-1.medium.com/max/949/1*eZpV33XI35nPNiWVE88ahA.png" width="949"></a></p><p class="medium-feed-snippet">How to choose right GPU and number of GPUs&#xA0;, and scale your LLM with more data.</p><p class="medium-feed-link"><a href="https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-b7ccaeb848a8?source=rss-23cc3547570------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@saniyajaswani12/how-to-scale-your-llm-training-b7ccaeb848a8?source=rss-23cc3547570------2</link>
            <guid isPermaLink="false">https://medium.com/p/b7ccaeb848a8</guid>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[reinforcement-learning]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[saniya jaswani]]></dc:creator>
            <pubDate>Tue, 10 Feb 2026 18:01:02 GMT</pubDate>
            <atom:updated>2026-02-10T18:01:02.300Z</atom:updated>
        </item>
    </channel>
</rss>