A plan for a big model: experts spread, any number of nodes, memory said

A mixture-of-experts model on more than one card is served with vLLM's
--enable-expert-parallel; config.json's experts are read by any of their
names, and a model that also reads pictures is sized by its text_config.
Tensor parallelism past the KV heads is allowed when it is a multiple of
them (Qwen3-235B, four KV heads, runs on eight cards), which the plan
had refused. Several nodes are offered in any number, not only powers of
two. Each way says what it needs of a card, part by part, and of all its
cards; the serve form checks a context longer than planned still fits.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-10-20 08:45:33 +02:00
1 parent 314cc5e6a3
commit 4fe9b46451
12 files changed
+257 -34

No files matched your search

+11 -7
View File
@@ -291,14 +291,14 @@ func planFiles(cmd *cobra.Command, client func() *ctlClient, repo, format string
}
fmt.Fprintln(out)
w := tabTo(out)
fmt.Fprintln(w, "FILE\tSIZE\tBEST WAY\tHOLDS\tOF\tNOW")
fmt.Fprintln(w, "FILE\tSIZE\tBEST WAY\tA CARD\tOF\tALL CARDS\tNOW")
for _, a := range p.Artifacts {
name := a.Name
if a.Shards > 1 && a.Format == "gguf" {
name += fmt.Sprintf(" (%d parts)", a.Shards)
}
if a.Best == nil {
fmt.Fprintf(w, "%s\t%s\tfits nowhere\t\t\t\n", name, bytesShort(a.Bytes))
fmt.Fprintf(w, "%s\t%s\tfits nowhere\t\t\t\t\n", name, bytesShort(a.Bytes))
continue
}
b := a.Best
@@ -306,11 +306,11 @@ func planFiles(cmd *cobra.Command, client func() *ctlClient, repo, format string
if b.FreeNow {
now = "free"
}
holds := fmt.Sprintf("%.1f GB a card", b.NeedGB)
holds, all := fmt.Sprintf("%.1f GB", b.NeedGB), fmt.Sprintf("%.0f GB", b.TotalGB())
if b.CPU {
holds = fmt.Sprintf("%.1f GB of RAM", b.NeedGB)
holds, all = fmt.Sprintf("%.1f GB of RAM", b.NeedGB), "-"
}
fmt.Fprintf(w, "%s\t%s\t%s\t%s\t%.0f GB\t%s\n", name, bytesShort(a.Bytes), b.Label(), holds, b.HaveGB, now)
fmt.Fprintf(w, "%s\t%s\t%s\t%s\t%.0f GB\t%s\t%s\n", name, bytesShort(a.Bytes), b.Label(), holds, b.HaveGB, all, now)
}
_ = w.Flush()
rec, ok := p.Recommended()
@@ -318,7 +318,11 @@ func planFiles(cmd *cobra.Command, client func() *ctlClient, repo, format string
fmt.Fprintln(out, "\nNo file fits this cluster as it is: a smaller context (--context), or more memory.")
return errDoesNotFit
}
fmt.Fprintf(out, "\nBest: %s on %s.\n", rec.Artifact, rec.Label())
fmt.Fprintf(out, "\nBest: %s on %s: %s.\n", rec.Artifact, rec.Label(), rec.MemoryText())
if p.KVBytesPerToken > 0 {
fmt.Fprintf(out, "The context costs %.2f GB per 1000 tokens, the whole model (--context to plan another).\n",
modelplan.GB(p.KVBytesPerToken*1000))
}
if len(p.Options) > 1 {
fmt.Fprintln(out, "\nEvery way, best first:")
w = tabTo(out)
@@ -327,7 +331,7 @@ func planFiles(cmd *cobra.Command, client func() *ctlClient, repo, format string
if o.FreeNow {
now = "free"
}
fmt.Fprintf(w, " %s\t%s\t%.1f of %.0f GB\t%d host(s)\t%s\n", o.Artifact, o.Label(), o.NeedGB, o.HaveGB, o.Hosts, now)
fmt.Fprintf(w, " %s\t%s\t%s\t%d host(s)\t%s\n", o.Artifact, o.Label(), o.MemoryText(), o.Hosts, now)
}
_ = w.Flush()
}
+14 -7
View File
@@ -107,11 +107,7 @@ func optionLabel(o modelplan.Option) string {
if o.FreeNow {
now = sOK.Render("free")
}
need := fmt.Sprintf("%.1f of %.0f GB a card", o.NeedGB, o.HaveGB)
if o.CPU {
need = fmt.Sprintf("%.1f GB of RAM", o.NeedGB)
}
return fmt.Sprintf("%s · %s · %s", o.Label(), need, now)
return fmt.Sprintf("%s · %s · %s", o.Label(), o.MemoryText(), now)
}
// repoMenu offers a repository's files, each with the best way it runs here;
@@ -197,8 +193,15 @@ func (m *consoleModel) serveForm(p modelserve.Plan, a modelserve.PlannedArtifact
if p.Note != "" {
note += "\n" + sWarn.Render("! ") + p.Note
}
note += fmt.Sprintf("\nPlanned for a %d-token context. The mirror fetches it and checks it, it joins the\n"+
"catalog, and a replica is started and asked to say hello.", p.Context)
note += fmt.Sprintf("\nMemory for a %d-token context, each way it runs:", p.Context)
for _, o := range opts {
note += "\n " + o.Label() + ": " + o.MemoryText()
}
if p.KVBytesPerToken > 0 {
note += fmt.Sprintf("\nThe context costs %.2f GB per 1000 tokens, the whole model; a longer one is checked\n"+
"before it is served.", modelplan.GB(p.KVBytesPerToken*1000))
}
note += "\nThe mirror fetches it and checks it, it joins the catalog, and a replica is started\nand asked to say hello."
ctxDefault := "4096"
if a.Format == "safetensors" {
ctxDefault = strconv.Itoa(p.Context)
@@ -234,6 +237,10 @@ func (m *consoleModel) serveForm(p modelserve.Plan, a modelserve.PlannedArtifact
req.File = a.Name
}
o := opts[slices.Index(where, v[4])]
// Asked for a context other than planned: does it still fit?
if sized := o.WithContext(p.KVBytesPerToken, ctxLen); !sized.Fits() {
return nil, fmt.Errorf("with a %d-token context it needs %s: a shorter context, or another way", ctxLen, sized.MemoryText())
}
if o.CPU {
req.CPU = true
} else {