<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
    <channel>
        <title>Open Source - Tag - Simi Studio</title>
        <link>/en/tags/open-source/</link>
        <description>Open Source - Tag - Simi Studio</description>
        <generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>simi@simi.studio (Simi)</managingEditor>
            <webMaster>simi@simi.studio (Simi)</webMaster><lastBuildDate>Mon, 30 Mar 2026 10:00:00 &#43;0800</lastBuildDate><atom:link href="/en/tags/open-source/" rel="self" type="application/rss+xml" /><item>
    <title>Qwen3.5-Omni: Alibaba Surpasses Gemini-3.1 Pro on 215 Audio-Video Tasks</title>
    <link>/en/posts/qwen-3-5-omni-multimodal/</link>
    <pubDate>Mon, 30 Mar 2026 10:00:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/qwen-3-5-omni-multimodal/</guid>
    <description><![CDATA[March 30, 2026—Alibaba Cloud releases Qwen3.5-Omni, achieving SOTA on 215 audio-video understanding and interaction tasks, surpassing Gemini-3.1 Pro. A significant breakthrough for Chinese LLMs in multimodal AI.]]></description>
</item>
<item>
    <title>OpenClaw Hits 25,000 GitHub Stars in 4 Weeks: What the Open Source AI Agent Boom Means</title>
    <link>/en/posts/openclaw-github-viral/</link>
    <pubDate>Sun, 01 Mar 2026 10:00:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/openclaw-github-viral/</guid>
    <description><![CDATA[March 2026—OpenClaw, an open-source AI Agent framework, gained 25,000 GitHub stars in 4 weeks, becoming one of the fastest-growing open-source Agent projects in GitHub history.]]></description>
</item>
<item>
    <title>Llama4-Swarm: Meta&#39;s Open-Source Answer to Thousand-Agent Collaboration</title>
    <link>/en/posts/llama4-swarm-distributed-ai/</link>
    <pubDate>Thu, 01 Jan 2026 10:00:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/llama4-swarm-distributed-ai/</guid>
    <description><![CDATA[January 1, 2026—Meta releases Llama4-Swarm, the first open-source model supporting real-time consensus decision-making across thousands of AI agents. A major leap for open-source AI collaboration.]]></description>
</item>
<item>
    <title>vLLM in Action: How to Run Open-Source LLMs Efficiently on GPU Servers</title>
    <link>/en/posts/vllm-local-llm-serving/</link>
    <pubDate>Sat, 15 Jun 2024 10:00:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/vllm-local-llm-serving/</guid>
    <description><![CDATA[vLLM is the most popular open-source LLM inference engine today. Its PagedAttention technology delivers 24x throughput improvement on the same hardware. This article explains what vLLM is, how to deploy it, and practical considerations.]]></description>
</item>
<item>
    <title>2024 Small Model Explosion: How Mistral 7B Changed the LLM Landscape</title>
    <link>/en/posts/small-open-source-models-2024/</link>
    <pubDate>Wed, 15 May 2024 10:00:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/small-open-source-models-2024/</guid>
    <description><![CDATA[2024 H1: small open-source models exploded. Mistral 7B, Phi-3, Gemma dropped one after another—3B/7B models now match GPT-3.5 performance. This article analyzes why and what it means for real work.]]></description>
</item>
<item>
    <title>Ollama in Practice: Running GPT-Level Models on Your Mac</title>
    <link>/en/posts/ollama-local-llm-guide/</link>
    <pubDate>Sat, 20 Apr 2024 10:00:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/ollama-local-llm-guide/</guid>
    <description><![CDATA[Ollama makes running LLMs locally trivial. One command to start a model, 7B runs smoothly on Mac. This is a practical guide covering setup, real performance numbers, and when to use local vs API.]]></description>
</item>
</channel>
</rss>
