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>
45 lines
1.4 KiB
Go
45 lines
1.4 KiB
Go
package store
|
|
|
|
import (
|
|
"context"
|
|
"time"
|
|
)
|
|
|
|
// NodeEngines are the engine builds chosen per node: node id, then engine,
|
|
// then the build ("cu129") or "none". A node or engine not here is left to
|
|
// the node's hardware.
|
|
func (s *DB) NodeEngines(ctx context.Context) (map[string]map[string]string, error) {
|
|
rows, err := s.db.QueryContext(ctx, `SELECT node_id, engine, variant FROM node_engines`)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
defer rows.Close()
|
|
out := map[string]map[string]string{}
|
|
for rows.Next() {
|
|
var node, engine, variant string
|
|
if err := rows.Scan(&node, &engine, &variant); err != nil {
|
|
return nil, err
|
|
}
|
|
if out[node] == nil {
|
|
out[node] = map[string]string{}
|
|
}
|
|
out[node][engine] = variant
|
|
}
|
|
return out, rows.Err()
|
|
}
|
|
|
|
// SetNodeEngine chooses an engine's build for a node; an empty variant
|
|
// leaves it to the node's hardware again.
|
|
func (s *DB) SetNodeEngine(ctx context.Context, node, engine, variant, by string) error {
|
|
if variant == "" {
|
|
_, err := s.db.ExecContext(ctx, `DELETE FROM node_engines WHERE node_id = ? AND engine = ?`, node, engine)
|
|
return err
|
|
}
|
|
_, err := s.db.ExecContext(ctx,
|
|
`INSERT INTO node_engines (node_id, engine, variant, updated_at, updated_by) VALUES (?, ?, ?, ?, ?)
|
|
ON CONFLICT (node_id, engine) DO UPDATE SET variant = excluded.variant,
|
|
updated_at = excluded.updated_at, updated_by = excluded.updated_by`,
|
|
node, engine, variant, time.Now().UnixMilli(), by)
|
|
return err
|
|
}
|