Refuse weights the nodes' llama.cpp cannot load, before fetching them
kev-0.5b declared architecture "ggmlc", which llama.cpp does not know. It was fetched, catalogued and placed, and failed on every node — while the answer was in the first kilobytes of the file. internal/gguf reads a GGUF header (v1-v3) up to general.architecture, over HTTP with a Range request, and judges it against the architectures llama.cpp b10991 lists in LLM_ARCH_NAMES (152, copied from the source at that tag); a vision projector is not a model on its own. An unknown build is not refused, only not vouched for, and a header that cannot be fetched does not refuse anything. Checked in three places: the registry listing (from the architecture Hugging Face reports with expand[]=gguf, so one request per repository) shows it and withholds the fetch button; a fetch reads the header and refuses unless "fetch anyway"; and the model service refuses to add such a model, which covers the serve form and ctl model add. Tried on real files: the mirror's qwen2.5-1.5b (qwen2) and bge-m3 (bert), and Qwen2.5-0.5B on Hugging Face through its redirect. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
c609805e4b
commit
f13b18149a
12 files changed
+782
-3
No files matched your search
@@ -5,6 +5,8 @@ import (
|
||||
"crypto/tls"
|
||||
"errors"
|
||||
"fmt"
|
||||
"gitea.mynodes.xyz/ilker/llmgw/internal/gguf"
|
||||
"gitea.mynodes.xyz/ilker/llmgw/internal/sourcecheck"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/http"
|
||||
@@ -150,6 +152,7 @@ func newServerCmd() *cobra.Command {
|
||||
// rather than accepting a model that vanishes on restart.
|
||||
if st := rt.Store(); st != nil {
|
||||
svc := modelsvc.New(cfg.Models, st, admin, log)
|
||||
svc.SetCheck(servableCheck(cfg.WantedEngines()["llamacpp"]))
|
||||
// Rebuild the catalog from configuration plus what was
|
||||
// stored, and put that in force — otherwise models added
|
||||
// before the last restart would be silently absent until
|
||||
@@ -535,3 +538,27 @@ func parseEndpointFlag(spec string) (config.Endpoint, error) {
|
||||
Weight: 1,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// servableCheck refuses a model whose llama.cpp weights the nodes' build
|
||||
// cannot load, read from the weights' own header before anything is placed.
|
||||
func servableCheck(llamaVersion string) func(context.Context, catalog.Model) error {
|
||||
return func(ctx context.Context, m catalog.Model) error {
|
||||
if llamaVersion == "" {
|
||||
return nil
|
||||
}
|
||||
usesLlama := false
|
||||
for _, p := range m.Profiles {
|
||||
if p.Engine == "llamacpp" {
|
||||
usesLlama = true
|
||||
}
|
||||
}
|
||||
url, ok := sourcecheck.HTTPSource(m.Source)
|
||||
if !usesLlama || !ok || !gguf.IsGGUF(url) {
|
||||
return nil
|
||||
}
|
||||
if v := gguf.Check(ctx, url, llamaVersion); !v.Servable {
|
||||
return fmt.Errorf("%s cannot be served: %s", m.Name, v.Reason)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user