Ilker ManapandClaude Opus 5.5
4f280a3546
A node that cannot run the CUDA 13 build installs the same version's CUDA 12.9 build from vLLM's GitHub release, with PyTorch's cu129 torch; the install computes on the GPU before it counts. The build can be chosen per node — auto, cu13, cu129, none — on the cluster page, with ctl engine-build, or over the admin API; the control plane keeps the choice and tells the node at once. Refs #2. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
50 lines
1.7 KiB
Go
50 lines
1.7 KiB
Go
package web
|
|
|
|
import (
|
|
"context"
|
|
"net/http"
|
|
"net/url"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/store"
|
|
)
|
|
|
|
// NodeEngineAdmin chooses an engine's build for a node: "auto", a build
|
|
// such as "cu129", or "none".
|
|
type NodeEngineAdmin interface {
|
|
SetNodeEngine(ctx context.Context, node, engine, build, by string) error
|
|
}
|
|
|
|
// RegisterNodeEngines mounts the choice of engine builds on the cluster
|
|
// page: for an administrator, with the session's CSRF token, and answered by
|
|
// going back to the page with what happened.
|
|
func (p *AccountPages) RegisterNodeEngines(mux *http.ServeMux, a NodeEngineAdmin) {
|
|
mux.HandleFunc("POST /admin/nodes/{id}/engines", p.adminOnly(func(w http.ResponseWriter, r *http.Request, admin store.User) {
|
|
sess, _, _ := p.session(r)
|
|
if !p.accounts.CheckCSRF(sess, r.FormValue("csrf")) {
|
|
http.Error(w, "bad request", http.StatusBadRequest)
|
|
return
|
|
}
|
|
node, engine, build := r.PathValue("id"), r.FormValue("engine"), r.FormValue("build")
|
|
q := url.Values{}
|
|
if err := a.SetNodeEngine(r.Context(), node, engine, build, admin.Email); err != nil {
|
|
p.log.Warn("an engine build was not chosen", "admin", admin.Email, "node", node, "err", err)
|
|
q.Set("problem", node+": "+err.Error())
|
|
} else {
|
|
p.log.Info("an engine build was chosen", "admin", admin.Email, "node", node, "engine", engine, "build", build)
|
|
q.Set("notice", node+" installs "+engine+" "+buildWords(build)+
|
|
"; the node is told now, and installs it in the background")
|
|
}
|
|
http.Redirect(w, r, "/admin?"+q.Encode(), http.StatusSeeOther)
|
|
}))
|
|
}
|
|
|
|
func buildWords(b string) string {
|
|
switch b {
|
|
case "auto":
|
|
return "in the build its hardware runs"
|
|
case "none":
|
|
return "no longer"
|
|
}
|
|
return "built for " + map[string]string{"cu13": "CUDA 13", "cu129": "CUDA 12.9"}[b]
|
|
}
|