Mirror a many-file model whole, with its checksums, for vLLM
The explorer fetches a safetensors set with its config and tokenizer; the mirror gives out a version's manifest only once nothing is downloading and every shard its index names is there, with each file's sha256, which nodes check; mirror add takes several URLs; a repository page is refused as a source. Refs #2 (item 9). Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
8957db30a2
commit
2735c5a318
13 files changed
+465
-34
No files matched your search
@@ -60,6 +60,9 @@ type repoSet struct {
|
||||
// A shard set goes as one action — a fifteen-shard model is not fifteen
|
||||
// decisions, it is one.
|
||||
Sources []repoSource
|
||||
// Companions are the files fetched with a safetensors set that are not
|
||||
// weights: config.json, the tokenizer, the shard index.
|
||||
Companions []string
|
||||
// Model and Version are what the fetch form starts with. Editable, because
|
||||
// the name a catalog entry uses is the operator's to choose and the
|
||||
// registry's idea of it is only a good guess.
|
||||
@@ -778,6 +781,17 @@ func (p *AccountPages) openRepo(r *http.Request, d *adminMirrorData, repo string
|
||||
rs.Sources = append(rs.Sources,
|
||||
repoSource{URL: got.DownloadURL("", f.Path), Path: f.Path})
|
||||
}
|
||||
// Safetensors are not a model on their own: vLLM loads a directory,
|
||||
// and reads its config and tokenizer before any weight. Fetched as
|
||||
// part of the set, or the set arrives as shards nothing can load.
|
||||
if strings.HasSuffix(strings.ToLower(set.Name), ".safetensors") {
|
||||
for _, f := range hf.Companions(got.Files) {
|
||||
rs.Sources = append(rs.Sources,
|
||||
repoSource{URL: got.DownloadURL("", f.Path), Path: f.Path})
|
||||
rs.Companions = append(rs.Companions, f.Path)
|
||||
rs.Bytes += f.Bytes
|
||||
}
|
||||
}
|
||||
d.RepoSets = append(d.RepoSets, rs)
|
||||
}
|
||||
p.probeKinds(r.Context(), d.RepoSets)
|
||||
|
||||
@@ -710,3 +710,37 @@ func TestARefusedFetchReturnsToItsFormAndAStartedOneToTheList(t *testing.T) {
|
||||
t.Errorf("a started download should be shown where it is followed: %s", body)
|
||||
}
|
||||
}
|
||||
|
||||
func TestASafetensorsSetIsFetchedWithWhatTheEngineReadsBesideIt(t *testing.T) {
|
||||
// The field: a four-shard AWQ model mirrored as its shards alone, and
|
||||
// vLLM failing at start for want of config.json.
|
||||
reg := &fakeRegistry{repo: hf.Repo{
|
||||
ID: "Qwen/Qwen2.5-32B-Instruct-AWQ", Revision: "abc123def456",
|
||||
Files: []hf.File{
|
||||
{Path: "model-00001-of-00002.safetensors", Bytes: 4_000_000_000},
|
||||
{Path: "model-00002-of-00002.safetensors", Bytes: 3_000_000_000},
|
||||
{Path: "model.safetensors.index.json", Bytes: 90_000},
|
||||
{Path: "config.json", Bytes: 900},
|
||||
{Path: "tokenizer.json", Bytes: 7_000_000},
|
||||
{Path: "tokenizer_config.json", Bytes: 7_000},
|
||||
{Path: "README.md", Bytes: 9_000},
|
||||
{Path: "modeling_custom.py", Bytes: 40_000},
|
||||
{Path: "onnx/config.json", Bytes: 900},
|
||||
},
|
||||
}}
|
||||
body := mirrorGet(t, mirrorPageWith(t, &fakeMirror{}, reg, true),
|
||||
"/admin/mirror?repo=Qwen/Qwen2.5-32B-Instruct-AWQ").Body.String()
|
||||
for _, want := range []string{"config.json", "tokenizer.json", "tokenizer_config.json", "model.safetensors.index.json"} {
|
||||
if !strings.Contains(body, `name="file" value="`+want+`"`) {
|
||||
t.Errorf("%s is not fetched with the set", want)
|
||||
}
|
||||
}
|
||||
for _, not := range []string{"README.md", "modeling_custom.py", "onnx/config.json"} {
|
||||
if strings.Contains(body, `name="file" value="`+not+`"`) {
|
||||
t.Errorf("%s was swept in with the set", not)
|
||||
}
|
||||
}
|
||||
if !strings.Contains(body, "with 4 files the engine reads beside them") {
|
||||
t.Errorf("the companions are not said; got %s", body)
|
||||
}
|
||||
}
|
||||
@@ -467,6 +467,7 @@ version and the old weights stay where they are.</p>
|
||||
{{range .RepoSets}}<tr>
|
||||
<td><code>{{.Name}}</code>
|
||||
{{if .Shards}}<span class="opt">{{.Shards}} shards, fetched together</span>{{end}}
|
||||
{{with .Companions}}<span class="opt" title="{{join .}}">with {{len .}} files the engine reads beside them</span>{{end}}
|
||||
{{if eq .Kind "adapter"}}<span class="tag new" title="a LoRA adapter: it runs on a {{.Arch}} model it was made for, not on its own">LoRA adapter · {{.Arch}}</span>
|
||||
{{else if eq .Kind "model"}}<span class="opt">model{{with .Arch}} · {{.}}{{end}}</span>{{end}}</td>
|
||||
<td class="num">{{bytes .Bytes}}</td>
|
||||
@@ -492,7 +493,8 @@ version and the old weights stay where they are.</p>
|
||||
</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
|
||||
a tokenizer. A safetensors set is fetched with the files vLLM reads beside it —
|
||||
config.json, the tokenizer, the shard index — and never with code. 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
|
||||
|
||||
Reference in new issue
Block a user