<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
        <title>LLM 推理 on vllbc02&#39;s blogs</title>
        <link>https://blog.vllbc.top/tags/llm-%E6%8E%A8%E7%90%86/</link>
        <description>Recent content in LLM 推理 on vllbc02&#39;s blogs</description>
        <generator>Hugo -- gohugo.io</generator>
        <language>zh-cn</language>
        <lastBuildDate>Fri, 06 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.vllbc.top/tags/llm-%E6%8E%A8%E7%90%86/index.xml" rel="self" type="application/rss+xml" /><item>
            <title>Chunked Prefill 与 PD 分离</title>
            <link>https://blog.vllbc.top/visual-reading/chunked-prefill-pd-disaggregation/</link>
            <pubDate>Fri, 06 Nov 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/chunked-prefill-pd-disaggregation/</guid>
            <description></description>
        </item><item>
            <title>CARFT</title>
            <link>https://blog.vllbc.top/visual-reading/carft/</link>
            <pubDate>Thu, 05 Nov 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/carft/</guid>
            <description></description>
        </item><item>
            <title>PagedAttention</title>
            <link>https://blog.vllbc.top/visual-reading/paged-attention-kv-cache/</link>
            <pubDate>Thu, 05 Nov 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/paged-attention-kv-cache/</guid>
            <description></description>
        </item><item>
            <title>Continuous Batching 与 vLLM 调度器</title>
            <link>https://blog.vllbc.top/visual-reading/continuous-batching-scheduler/</link>
            <pubDate>Thu, 05 Nov 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/continuous-batching-scheduler/</guid>
            <description></description>
        </item><item>
            <title>CUDA Graphs 与 LLM 解码执行</title>
            <link>https://blog.vllbc.top/visual-reading/cuda-graphs-execution/</link>
            <pubDate>Fri, 06 Nov 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/cuda-graphs-execution/</guid>
            <description></description>
        </item><item>
            <title>Speculative Decoding</title>
            <link>https://blog.vllbc.top/visual-reading/speculative-decoding/</link>
            <pubDate>Fri, 06 Nov 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/speculative-decoding/</guid>
            <description></description>
        </item></channel>
</rss>
