deploy: 2f73eaed9a

2025-10-04 17:44:58 +00:00
parent c8d7b92351
commit 175644c1bf
26 changed files with 27 additions and 27 deletions
--- a/posts/benchmarking-llms-on-jetson-orin-nano/index.html
+++ b/posts/benchmarking-llms-on-jetson-orin-nano/index.html
@@ -8,7 +8,7 @@
 NVIDIA&rsquo;s Jetson Orin Nano promises impressive specs: 1024 CUDA cores, 32 Tensor Cores, and 40 TOPS of INT8 compute performance packed into a compact, power-efficient edge device. On paper, it looks like a capable platform for running Large Language Models locally. But there&rsquo;s a catch—one that reveals a fundamental tension in modern edge AI hardware design.
 After running 66 inference tests across seven different language models ranging from 0.5B to 5.4B parameters, I discovered something counterintuitive: the device&rsquo;s computational muscle sits largely idle during LLM inference. The bottleneck isn&rsquo;t computation—it&rsquo;s memory bandwidth. This isn&rsquo;t just a quirk of one device; it&rsquo;s a reality that affects how we should think about deploying LLMs at the edge."><meta name=keywords content="software engineer,performance engineering,Google engineer,tech blog,software development,performance optimization,Eric Liu,engineering blog,mountain biking,Jeep enthusiast,overlanding,camping,outdoor adventures"><meta name=twitter:card content="summary"><meta name=twitter:title content="Why Your Jetson Orin Nano's 40 TOPS Goes Unused (And What That Means for Edge AI)"><meta name=twitter:description content="Introduction Link to heading NVIDIA’s Jetson Orin Nano promises impressive specs: 1024 CUDA cores, 32 Tensor Cores, and 40 TOPS of INT8 compute performance packed into a compact, power-efficient edge device. On paper, it looks like a capable platform for running Large Language Models locally. But there’s a catch—one that reveals a fundamental tension in modern edge AI hardware design.
 After running 66 inference tests across seven different language models ranging from 0.5B to 5.4B parameters, I discovered something counterintuitive: the device’s computational muscle sits largely idle during LLM inference. The bottleneck isn’t computation—it’s memory bandwidth. This isn’t just a quirk of one device; it’s a reality that affects how we should think about deploying LLMs at the edge."><meta property="og:url" content="/posts/benchmarking-llms-on-jetson-orin-nano/"><meta property="og:site_name" content="Eric X. Liu's Personal Page"><meta property="og:title" content="Why Your Jetson Orin Nano's 40 TOPS Goes Unused (And What That Means for Edge AI)"><meta property="og:description" content="Introduction Link to heading NVIDIA’s Jetson Orin Nano promises impressive specs: 1024 CUDA cores, 32 Tensor Cores, and 40 TOPS of INT8 compute performance packed into a compact, power-efficient edge device. On paper, it looks like a capable platform for running Large Language Models locally. But there’s a catch—one that reveals a fundamental tension in modern edge AI hardware design.
-After running 66 inference tests across seven different language models ranging from 0.5B to 5.4B parameters, I discovered something counterintuitive: the device’s computational muscle sits largely idle during LLM inference. The bottleneck isn’t computation—it’s memory bandwidth. This isn’t just a quirk of one device; it’s a reality that affects how we should think about deploying LLMs at the edge."><meta property="og:locale" content="en"><meta property="og:type" content="article"><meta property="article:section" content="posts"><meta property="article:published_time" content="2025-10-04T00:00:00+00:00"><meta property="article:modified_time" content="2025-10-04T17:44:11+00:00"><link rel=canonical href=/posts/benchmarking-llms-on-jetson-orin-nano/><link rel=preload href=/fonts/fa-brands-400.woff2 as=font type=font/woff2 crossorigin><link rel=preload href=/fonts/fa-regular-400.woff2 as=font type=font/woff2 crossorigin><link rel=preload href=/fonts/fa-solid-900.woff2 as=font type=font/woff2 crossorigin><link rel=stylesheet href=/css/coder.min.f03d6359cf766772af14fbe07ce6aca734b321c2e15acba0bbf4e2254941c460.css integrity="sha256-8D1jWc92Z3KvFPvgfOaspzSzIcLhWsugu/TiJUlBxGA=" crossorigin=anonymous media=screen><link rel=stylesheet href=/css/coder-dark.min.a00e6364bacbc8266ad1cc81230774a1397198f8cfb7bcba29b7d6fcb54ce57f.css integrity="sha256-oA5jZLrLyCZq0cyBIwd0oTlxmPjPt7y6KbfW/LVM5X8=" crossorigin=anonymous media=screen><link rel=icon type=image/svg+xml href=/images/favicon.svg sizes=any><link rel=icon type=image/png href=/images/favicon-32x32.png sizes=32x32><link rel=icon type=image/png href=/images/favicon-16x16.png sizes=16x16><link rel=apple-touch-icon href=/images/apple-touch-icon.png><link rel=apple-touch-icon sizes=180x180 href=/images/apple-touch-icon.png><link rel=manifest href=/site.webmanifest><link rel=mask-icon href=/images/safari-pinned-tab.svg color=#5bbad5></head><body class="preload-transitions colorscheme-auto"><div class=float-container><a id=dark-mode-toggle class=colorscheme-toggle><i class="fa-solid fa-adjust fa-fw" aria-hidden=true></i></a></div><main class=wrapper><nav class=navigation><section class=container><a class=navigation-title href=/>Eric X. Liu's Personal Page
+After running 66 inference tests across seven different language models ranging from 0.5B to 5.4B parameters, I discovered something counterintuitive: the device’s computational muscle sits largely idle during LLM inference. The bottleneck isn’t computation—it’s memory bandwidth. This isn’t just a quirk of one device; it’s a reality that affects how we should think about deploying LLMs at the edge."><meta property="og:locale" content="en"><meta property="og:type" content="article"><meta property="article:section" content="posts"><meta property="article:published_time" content="2025-10-04T00:00:00+00:00"><meta property="article:modified_time" content="2025-10-04T17:44:47+00:00"><link rel=canonical href=/posts/benchmarking-llms-on-jetson-orin-nano/><link rel=preload href=/fonts/fa-brands-400.woff2 as=font type=font/woff2 crossorigin><link rel=preload href=/fonts/fa-regular-400.woff2 as=font type=font/woff2 crossorigin><link rel=preload href=/fonts/fa-solid-900.woff2 as=font type=font/woff2 crossorigin><link rel=stylesheet href=/css/coder.min.f03d6359cf766772af14fbe07ce6aca734b321c2e15acba0bbf4e2254941c460.css integrity="sha256-8D1jWc92Z3KvFPvgfOaspzSzIcLhWsugu/TiJUlBxGA=" crossorigin=anonymous media=screen><link rel=stylesheet href=/css/coder-dark.min.a00e6364bacbc8266ad1cc81230774a1397198f8cfb7bcba29b7d6fcb54ce57f.css integrity="sha256-oA5jZLrLyCZq0cyBIwd0oTlxmPjPt7y6KbfW/LVM5X8=" crossorigin=anonymous media=screen><link rel=icon type=image/svg+xml href=/images/favicon.svg sizes=any><link rel=icon type=image/png href=/images/favicon-32x32.png sizes=32x32><link rel=icon type=image/png href=/images/favicon-16x16.png sizes=16x16><link rel=apple-touch-icon href=/images/apple-touch-icon.png><link rel=apple-touch-icon sizes=180x180 href=/images/apple-touch-icon.png><link rel=manifest href=/site.webmanifest><link rel=mask-icon href=/images/safari-pinned-tab.svg color=#5bbad5></head><body class="preload-transitions colorscheme-auto"><div class=float-container><a id=dark-mode-toggle class=colorscheme-toggle><i class="fa-solid fa-adjust fa-fw" aria-hidden=true></i></a></div><main class=wrapper><nav class=navigation><section class=container><a class=navigation-title href=/>Eric X. Liu's Personal Page
 </a><input type=checkbox id=menu-toggle>
 <label class="menu-button float-right" for=menu-toggle><i class="fa-solid fa-bars fa-fw" aria-hidden=true></i></label><ul class=navigation-list><li class=navigation-item><a class=navigation-link href=/posts/>Posts</a></li><li class=navigation-item><a class=navigation-link href=https://chat.ericxliu.me>Chat</a></li><li class=navigation-item><a class=navigation-link href=https://git.ericxliu.me/user/oauth2/Authenitk>Git</a></li><li class=navigation-item><a class=navigation-link href=https://coder.ericxliu.me/api/v2/users/oidc/callback>Coder</a></li><li class=navigation-item><a class=navigation-link href=/>|</a></li><li class=navigation-item><a class=navigation-link href=https://sso.ericxliu.me>Sign in</a></li></ul></section></nav><div class=content><section class="container post"><article><header><div class=post-title><h1 class=title><a class=title-link href=/posts/benchmarking-llms-on-jetson-orin-nano/>Why Your Jetson Orin Nano's 40 TOPS Goes Unused (And What That Means for Edge AI)</a></h1></div><div class=post-meta><div class=date><span class=posted-on><i class="fa-solid fa-calendar" aria-hidden=true></i>
 <time datetime=2025-10-04T00:00:00Z>October 4, 2025
@@ -25,7 +25,7 @@ After running 66 inference tests across seven different language models ranging
 <a class=heading-link href=#the-testing-process><i class="fa-solid fa-link" aria-hidden=true title="Link to heading"></i>
 <span class=sr-only>Link to heading</span></a></h3><p>Each model faced 10-12 prompts of varying complexity—from simple arithmetic to technical explanations about LLMs themselves. Out of 84 planned tests, 66 completed successfully (78.6% success rate). The failures? Mostly out-of-memory crashes on larger models and occasional inference engine instability.</p><h3 id=understanding-the-limits-roofline-analysis>Understanding the Limits: Roofline Analysis
 <a class=heading-link href=#understanding-the-limits-roofline-analysis><i class="fa-solid fa-link" aria-hidden=true title="Link to heading"></i>
-<span class=sr-only>Link to heading</span></a></h3><p>To understand where performance hits its ceiling, I applied roofline analysis—a method that reveals whether a workload is compute-bound (limited by processing power) or memory-bound (limited by data transfer speed). For each model, I calculated:</p><ul><li><strong>FLOPs per token</strong>: Approximately 2 × total_parameters (accounting for matrix multiplications in forward pass)</li><li><strong>Bytes per token</strong>: model_size × 1.1 (including 10% overhead for activations and KV cache)</li><li><strong>Operational Intensity (OI)</strong>: FLOPs per token / Bytes per token</li><li><strong>Theoretical performance</strong>: min(compute_limit, bandwidth_limit)</li></ul><p>The roofline model works by comparing a workload&rsquo;s operational intensity (how many calculations you do per byte of data moved) against the device&rsquo;s balance point. If your operational intensity is too low, you&rsquo;re bottlenecked by memory bandwidth—and as we&rsquo;ll see, that&rsquo;s exactly what happens with LLM inference.</p><p><img src=/images/benchmarking-llms-on-jetson-orin-nano/388f43c3f800483aae5ea487e8f45922.png alt="S3 File"></p><h2 id=the-results-speed-and-efficiency>The Results: Speed and Efficiency
+<span class=sr-only>Link to heading</span></a></h3><p>To understand where performance hits its ceiling, I applied roofline analysis—a method that reveals whether a workload is compute-bound (limited by processing power) or memory-bound (limited by data transfer speed). For each model, I calculated:</p><ul><li><strong>FLOPs per token</strong>: Approximately 2 × total_parameters (accounting for matrix multiplications in forward pass)</li><li><strong>Bytes per token</strong>: model_size × 1.1 (including 10% overhead for activations and KV cache)</li><li><strong>Operational Intensity (OI)</strong>: FLOPs per token / Bytes per token</li><li><strong>Theoretical performance</strong>: min(compute_limit, bandwidth_limit)</li></ul><p>The roofline model works by comparing a workload&rsquo;s operational intensity (how many calculations you do per byte of data moved) against the device&rsquo;s balance point. If your operational intensity is too low, you&rsquo;re bottlenecked by memory bandwidth—and as we&rsquo;ll see, that&rsquo;s exactly what happens with LLM inference.</p><p><img src=/images/benchmarking-llms-on-jetson-orin-nano/16d64bdc9cf14b05b7c40c4718b8091b.png alt="S3 File"></p><h2 id=the-results-speed-and-efficiency>The Results: Speed and Efficiency
 <a class=heading-link href=#the-results-speed-and-efficiency><i class="fa-solid fa-link" aria-hidden=true title="Link to heading"></i>
 <span class=sr-only>Link to heading</span></a></h2><h3 id=what-actually-runs-fast>What Actually Runs Fast
 <a class=heading-link href=#what-actually-runs-fast><i class="fa-solid fa-link" aria-hidden=true title="Link to heading"></i>
@@ -62,4 +62,4 @@ After running 66 inference tests across seven different language models ranging
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/breville-barista-pro-maintenance/index.html
+++ b/posts/breville-barista-pro-maintenance/index.html
@@ -25,4 +25,4 @@ Understanding the Two Primary Maintenance Cycles Link to heading The Breville Ba
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/espresso-theory-application-a-guide-for-the-breville-barista-pro/index.html
+++ b/posts/espresso-theory-application-a-guide-for-the-breville-barista-pro/index.html
@@ -20,4 +20,4 @@ Our overarching philosophy is simple: isolate and change only one variable at a
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/flashing-jetson-orin-nano-in-virtualized-environments/index.html
+++ b/posts/flashing-jetson-orin-nano-in-virtualized-environments/index.html
@@ -168,4 +168,4 @@ Flashing NVIDIA Jetson devices remotely presents unique challenges when the host
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/how-rvq-teaches-llms-to-see-and-hear/index.html
+++ b/posts/how-rvq-teaches-llms-to-see-and-hear/index.html
@@ -18,4 +18,4 @@ The answer lies in creating a universal language—a bridge between the continuo
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/index.html
+++ b/posts/index.html
@@ -14,4 +14,4 @@
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/index.xml
+++ b/posts/index.xml
@@ -1,4 +1,4 @@
-<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Posts on Eric X. Liu's Personal Page</title><link>/posts/</link><description>Recent content in Posts on Eric X. Liu's Personal Page</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 04 Oct 2025 17:44:11 +0000</lastBuildDate><atom:link href="/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>Why Your Jetson Orin Nano's 40 TOPS Goes Unused (And What That Means for Edge AI)</title><link>/posts/benchmarking-llms-on-jetson-orin-nano/</link><pubDate>Sat, 04 Oct 2025 00:00:00 +0000</pubDate><guid>/posts/benchmarking-llms-on-jetson-orin-nano/</guid><description>&lt;h2 id="introduction"&gt;
+<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Posts on Eric X. Liu's Personal Page</title><link>/posts/</link><description>Recent content in Posts on Eric X. Liu's Personal Page</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 04 Oct 2025 17:44:47 +0000</lastBuildDate><atom:link href="/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>Why Your Jetson Orin Nano's 40 TOPS Goes Unused (And What That Means for Edge AI)</title><link>/posts/benchmarking-llms-on-jetson-orin-nano/</link><pubDate>Sat, 04 Oct 2025 00:00:00 +0000</pubDate><guid>/posts/benchmarking-llms-on-jetson-orin-nano/</guid><description>&lt;h2 id="introduction"&gt;
 Introduction
 &lt;a class="heading-link" href="#introduction"&gt;
 &lt;i class="fa-solid fa-link" aria-hidden="true" title="Link to heading"&gt;&lt;/i&gt;
--- a/posts/mixture-of-experts-moe-models-challenges-solutions-in-practice/index.html
+++ b/posts/mixture-of-experts-moe-models-challenges-solutions-in-practice/index.html
@@ -44,4 +44,4 @@ The <strong>Top-K routing</strong> mechanism, as illustrated in the provided ima
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/openwrt-mwan3-wireguard-endpoint-exclusion/index.html
+++ b/posts/openwrt-mwan3-wireguard-endpoint-exclusion/index.html
@@ -98,4 +98,4 @@ When using WireGuard together with MWAN3 on OpenWrt, the tunnel can fail to esta
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/page/2/index.html
+++ b/posts/page/2/index.html
@@ -9,4 +9,4 @@
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/ppo-for-language-models/index.html
+++ b/posts/ppo-for-language-models/index.html
@@ -25,4 +25,4 @@ where <code>δ_t = r_t + γV(s_{t+1}) - V(s_t)</code></p><ul><li><strong>γ (gam
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/quantization-in-llms/index.html
+++ b/posts/quantization-in-llms/index.html
@@ -7,4 +7,4 @@
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/secure-boot-dkms-and-mok-on-proxmox-debian/index.html
+++ b/posts/secure-boot-dkms-and-mok-on-proxmox-debian/index.html
@@ -59,4 +59,4 @@ nvidia-smi failed to communicate with the NVIDIA driver modprobe nvidia → “K
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/supabase-deep-dive/index.html
+++ b/posts/supabase-deep-dive/index.html
@@ -90,4 +90,4 @@ Supabase enters this space with a radically different philosophy: transparency.
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/t5-the-transformer-that-zigged-when-others-zagged-an-architectural-deep-dive/index.html
+++ b/posts/t5-the-transformer-that-zigged-when-others-zagged-an-architectural-deep-dive/index.html
@@ -30,4 +30,4 @@ But to truly understand the field, we must look at the pivotal models that explo
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/transformer-s-core-mechanics/index.html
+++ b/posts/transformer-s-core-mechanics/index.html
@@ -36,4 +36,4 @@ In deep learning, a &ldquo;channel&rdquo; can be thought of as a feature dimensi
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/unifi-vlan-migration-to-zone-based-architecture/index.html
+++ b/posts/unifi-vlan-migration-to-zone-based-architecture/index.html
@@ -28,4 +28,4 @@ This article documents that journey. It details the pitfalls encountered, the co
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
--- a/posts/useful/index.html
+++ b/posts/useful/index.html
@@ -9,4 +9,4 @@ One-minute read</span></div></div></header><div class=post-content><ul><li><a hr
 2016 -
 2025
 Eric X. Liu
-<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/85e0d05">[85e0d05]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>
+<a href="https://git.ericxliu.me/eric/ericxliu-me/commit/2f73eae">[2f73eae]</a></section></footer></main><script src=/js/coder.min.6ae284be93d2d19dad1f02b0039508d9aab3180a12a06dcc71b0b0ef7825a317.js integrity="sha256-auKEvpPS0Z2tHwKwA5UI2aqzGAoSoG3McbCw73gloxc="></script><script defer src=https://static.cloudflareinsights.com/beacon.min.js data-cf-beacon='{"token": "987638e636ce4dbb932d038af74c17d1"}'></script></body></html>