llmgw/internal/web/templates/admin_mirror.html

{{define "admin_mirror"}}<!doctype html>
<html lang="en"><head>
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
{{/* Only while something is downloading. A reload at any other time would
     take with it whatever the operator was typing into the form below. */}}
{{if .RefreshSec}}<meta http-equiv="refresh" content="{{.RefreshSec}}">{{end}}
<title>Mirror · llmgw</title><link rel="stylesheet" href="/_static/base.css">
</head><body><div class="wrap">
<header>
  <h1>Model mirror</h1>
  <p class="sub">
    {{if .Unreachable}}{{.Addr}} did not answer{{else}}{{.Present}} held ·
    {{.Fetching}} downloading · {{.Failed}} failed · {{.Addr}}{{end}}
  </p>
  <nav><a href="/admin">cluster</a> <a href="/admin/users">accounts</a>
       <a href="/profile">your keys</a></nav>
</header>

{{if .Error}}<p class="error">{{.Error}}</p>{{end}}
{{if .Message}}<p class="ok">{{.Message}}</p>{{end}}

{{if .Unreachable}}
{{/* Said outright rather than shown as an empty table. A mirror holding
     nothing and a mirror that is not there look the same in a list of zero
     rows, and they call for opposite responses. */}}
<p class="note">Nothing was read from the mirror, so this page is not a list of
what it holds — it is not currently reachable at <code>{{.Addr}}</code>. Check
that <code>llmgw-mirror</code> is running there and that its management port is
reachable from this machine.</p>
{{else}}

<h2>What the mirror holds</h2>
{{if .Rows}}
<table>
<tr><th>Model</th><th>Version</th><th>File</th><th>State</th><th>Size</th>
    <th>Checksum</th><th></th></tr>
{{range .Rows}}<tr>
  <td>{{.Model}}</td>
  <td>{{.Version}}</td>
  <td><code>{{.File}}</code></td>
  <td class="state state-{{.State}}">{{.State}}</td>
  <td class="num">
    {{if eq (printf "%s" .State) "fetching"}}
      {{if .HasPercent}}{{bytes .BytesDone}} / {{bytes .BytesTotal}} ({{.Percent}}%)
      {{else}}{{/* No total came from upstream, so no percentage is invented —
                   a bar that guesses its own end and then stops moving is worse
                   than a number that only goes up. */}}
      {{bytes .BytesDone}} so far{{end}}
    {{else if eq (printf "%s" .State) "failed"}}—
    {{else}}{{bytes .BytesDone}}{{end}}
  </td>
  <td>{{if .SHA256}}<code title="{{.SHA256}}">{{slice .SHA256 0 12}}</code>{{else}}—{{end}}</td>
  <td>
    {{if eq (printf "%s" .State) "fetching"}}
      <span class="note">downloading</span>
    {{else if eq (printf "%s" .State) "failed"}}
    {{/* Retry, not remove. A fetch that failed left nothing on disk, so the
         remove would come back "the mirror holds nothing for this" — a button
         whose only outcome is a confusing error. Starting the same download
         again is what somebody looking at a failed row wants, and the mirror
         allows it: only a download still running is refused. */}}
    <form method="post" action="/admin/mirror/fetch" class="inline">
      <input type="hidden" name="csrf" value="{{$.CSRF}}">
      <input type="hidden" name="source" value="{{.Source}}">
      <input type="hidden" name="model" value="{{.Model}}">
      <input type="hidden" name="version" value="{{.Version}}">
      <input type="hidden" name="file" value="{{.File}}">
      <button type="submit" class="link">Retry</button>
    </form>
    {{else}}
    {{if $.HasCatalog}}{{if .Serve}}<a href="/admin/mirror">close</a>
    {{else}}<a href="/admin/mirror?serve={{.Model}}:{{.Version}}">serve</a>{{end}}
    {{end}}
    <form method="post" action="/admin/mirror/{{.Model}}/{{.Version}}/remove"
          class="inline" onsubmit="return confirm('Remove {{.Model}}/{{.Version}} and every file in it?')">
      <input type="hidden" name="csrf" value="{{$.CSRF}}">
      <button type="submit" class="link danger">Remove</button>
    </form>
    {{end}}
  </td>
</tr>
{{if .Err}}<tr><td colspan="7" class="error-row">{{.Err}}</td></tr>{{end}}
{{if not .Err}}<tr><td colspan="7" class="url-row"><code>{{.URL}}</code></td></tr>{{end}}

{{with .Serve}}
<tr class="editing"><td colspan="7">
{{if .Refusal}}
{{/* Offered and then failing at placement is worse than not offered at all. */}}
<p class="error">Cannot be served as it stands: {{.Refusal}}.</p>
{{else}}
{{if .Warning}}<p class="note error-row">{{.Warning}}.</p>{{end}}
<form method="post" action="/admin/mirror/serve">
  <input type="hidden" name="csrf" value="{{$.CSRF}}">
  <input type="hidden" name="source" value="{{.Source}}">
  <input type="hidden" name="engine" value="{{.Engine}}">
  <p class="sub">Serving <code>{{.Source}}</code> with <strong>{{.Engine}}</strong>.
  {{if .Files}}The whole version, {{.Files}} files: the node fetches them into one
  directory and the engine is given the directory.{{end}}</p>
  <div class="field-row">
    <label>Name <input type="text" name="name" value="{{.Model}}" required></label>
    <label>Aliases <span class="opt">comma separated</span>
      <input type="text" name="aliases" placeholder="coder-7b"></label>
    <label>Replicas <input type="text" name="replicas" value="1" required></label>
  </div>
  {{/* Reaches clients through /v1/models, which for most of them is the only
       view of what this gateway serves. Nine names and nothing to choose
       between them is a choice made by guesswork. */}}
  <label>What it is for <span class="opt">shown to clients in /v1/models</span>
    <input type="text" name="description"
           placeholder="general chat, strong Swedish; 14B, slower than the 8B"></label>
  <div class="field-row">
    <label>Context a request may use
      <input type="text" name="context_length" value="4096" required></label>
    <label>Output limit <span class="opt">optional</span>
      <input type="text" name="max_output" value="1024"></label>
    <label>Engine context pool <span class="opt">divided across slots</span>
      <input type="text" name="ctx_size" value="16384"></label>
  </div>
  <div class="field-row">
    <label>Profile name <input type="text" name="profile" value="{{.Profile}}"></label>
    <label>Needs RAM (GB) <span class="opt">estimated from the weights</span>
      <input type="text" name="min_memory_gb" value="{{.MinMemoryGB}}"></label>
    <label>Only nodes labelled <span class="opt">key / value, optional</span>
      <input type="text" name="selector_key" placeholder="role" size="8">
      <input type="text" name="selector_value" placeholder="cpu-large" size="10"></label>
  </div>
  <button type="submit">Add to the catalog</button>
</form>
<p class="note">The context pool is what the engine is given; llama.cpp divides
it across its parallel slots, so the number one request may use is the smaller
one above.</p>
<p class="note">The memory figure is the weights plus half again for the KV pool
plus two for the engine — an estimate, and editable. It is filled in rather than
left blank because a CPU profile has no card to be short of: with no figure,
every ready node is a candidate and the first one picked is whichever the
scheduler reached, not whichever can hold the model. A node label does the same
job by name if you would rather pin it.</p>
{{end}}
</td></tr>
{{end}}
{{end}}
</table>
<p class="note">The address under each row is what a catalog entry should say.
It is rendered here rather than assembled by hand because the mirror and the
catalog have to spell the same file the same way — two spellings is what makes a
file that is in use look unreferenced.</p>
{{else}}<p class="empty">The mirror is reachable and holds nothing yet.</p>{{end}}

{{if .HasRegistry}}
<h2>Find a model</h2>
<form method="get" action="/admin/mirror">
  <label>Search Hugging Face
    <input type="text" name="q" value="{{.Query}}" placeholder="qwen2.5 coder gguf"></label>
  <button type="submit">Search</button>
</form>

{{if .RegistryErr}}
{{/* Its own line, not the page's error: the registry is somebody else's server
     and it being down says nothing about the mirror, which is what this page is
     for and has to keep working when Hugging Face does not. */}}
<p class="note error-row">The registry: {{.RegistryErr}}</p>
{{end}}

{{if .Results}}
<table><tr><th>Repository</th><th>Downloads</th><th>Task</th><th></th></tr>
{{range .Results}}<tr>
  <td><code>{{.ID}}</code>{{if .Gated.Is}} <span class="opt">gated</span>{{end}}</td>
  <td class="num">{{compact .Downloads}}</td>
  <td>{{or .PipelineTag "—"}}</td>
  <td><a href="/admin/mirror?q={{$.Query}}&amp;repo={{.ID}}">files</a></td>
</tr>{{end}}
</table>
<p class="note">A gated repository needs its terms accepted with a Hugging Face
account, and this browses anonymously — the files will list, and fetching one
will fail at the mirror. Download it by hand and put it in the mirror
directory, or give the mirror a token.</p>
{{else if .Query}}{{if not .RegistryErr}}
<p class="empty">Nothing matched “{{.Query}}”.</p>
{{end}}{{end}}

{{if .Repo}}
<h3>{{.Repo.ID}} <span class="opt">at {{.Repo.ShortRevision}}</span></h3>
{{if .RepoSets}}
<table>
<tr><th>What</th><th>Size</th><th>Published checksum</th><th></th></tr>
{{range .RepoSets}}<tr>
  <td><code>{{.Name}}</code>
    {{if .Shards}}<span class="opt">{{.Shards}} shards, fetched together</span>{{end}}</td>
  <td class="num">{{bytes .Bytes}}</td>
  <td>{{with .SHA256}}<code title="{{.}}">{{slice . 0 12}}</code>{{else}}—{{end}}</td>
  <td>
    <form method="post" action="/admin/mirror/fetch" class="inline">
      <input type="hidden" name="csrf" value="{{$.CSRF}}">
      {{range .Sources}}<input type="hidden" name="source" value="{{.URL}}">
      <input type="hidden" name="file" value="{{.Path}}">
      {{end}}
      <input type="text" name="model" value="{{.Model}}" size="24">
      <input type="text" name="version" value="{{.Version}}" size="10">
      <button type="submit">Fetch</button>
    </form>
  </td>
</tr>{{end}}
</table>
<p class="note">Only the weights are listed; a repository is mostly a README and
a tokenizer. Shards of one file are one row and one button — a fifteen-shard
model is one decision, not fifteen. Two separate files are two rows because they
are usually alternatives: one quantisation or the other, not both.</p>
<p class="note">The source URLs are pinned to
<code>{{.Repo.ShortRevision}}</code> rather than to a branch, so what arrives is
what is listed here even if the branch moves in between — and a single file's
checksum above is what the registry publishes, to compare with what the mirror
computes once it has it.</p>
{{else}}
<p class="empty">No weight files in {{.Repo.ID}}.</p>
{{end}}
{{end}}
{{end}}

<h2>Fetch a model</h2>
<p class="note">By hand, for anything the search does not reach.</p>
<form method="post" action="/admin/mirror/fetch">
  <input type="hidden" name="csrf" value="{{.CSRF}}">
  <label>Source URL
    <input type="text" name="source" required
           placeholder="https://huggingface.co/…/resolve/main/model.gguf"></label>
  <div class="field-row">
    <label>Model <input type="text" name="model" required placeholder="qwen2.5-coder-7b"></label>
    <label>Version <input type="text" name="version" required placeholder="2026-09"></label>
    <label>File <span class="opt">optional</span>
      <input type="text" name="file" placeholder="taken from the URL"></label>
  </div>
  <button type="submit">Start download</button>
</form>
<p class="note">The mirror answers as soon as the download is under way, not when
it finishes — a model is tens of gigabytes and nothing here holds a connection
open for that. The row above will show it arriving. A version is never
overwritten: fetching into one that exists is refused, so a new build is a new
version and the old weights stay where they are.</p>
{{end}}

<footer><span>llmgw {{.Version}}</span><span>{{.Now}}</span></footer>
</div></body></html>{{end}}