Decide engines per node, and let a node join without one it cannot run

engine_overrides give nodes picked by GPU class, id or labels their own
engine versions; node add --disable-engine keeps one off a node; what
vLLM cannot do on a node is a warning rather than a refused node; the
CUDA requirement follows the version; a hand-named binary is no longer
replaced by an installed one.

Refs #2 (items 4 and 7).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-10-01 12:07:25 +02:00
1 parent cba3e329fc
commit e313f32696
21 files changed
+532 -62

No files matched your search

+9 -5
View File
@@ -208,10 +208,13 @@ type NodeView struct {
// GPUView is one card as a node's page shows it.
type GPUView struct {
Index int `json:"index"`
Name string `json:"name"`
NUMA int `json:"numa"`
NVLinkPeers []int `json:"nvlink_peers,omitempty"`
Index int `json:"index"`
Name string `json:"name"`
// ComputeCapability is what decides which engine builds run on the card:
// CUDA 13 builds need 7.5, so a V100 (7.0) runs only older ones.
ComputeCapability string `json:"compute_capability,omitempty"`
NUMA int `json:"numa"`
NVLinkPeers []int `json:"nvlink_peers,omitempty"`
// NearestNIC is the adapter closest to the card, and how close.
NearestNIC string `json:"nearest_nic,omitempty"`
NICPath string `json:"nic_path,omitempty"`
@@ -497,7 +500,8 @@ func (a *API) Nodes() []NodeView {
v.Load = loadView(n.Load, time.Now())
v.NVLinkDomain, v.IMEX, v.IMEXChannels = n.NVLinkDomain(), n.IMEX.State, n.IMEX.Channels
for _, g := range n.GPUs {
gv := GPUView{Index: g.Index, Name: g.Name, NUMA: g.NUMANode, NVLinkPeers: g.NVLinkPeers}
gv := GPUView{Index: g.Index, Name: g.Name, ComputeCapability: g.ComputeCapability,
NUMA: g.NUMANode, NVLinkPeers: g.NVLinkPeers}
for hca, rel := range g.NICPaths {
if gv.NearestNIC == "" || discovery.PathRank(rel) < discovery.PathRank(gv.NICPath) ||
(discovery.PathRank(rel) == discovery.PathRank(gv.NICPath) && hca < gv.NearestNIC) {