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

+20 -1
View File
@@ -12,6 +12,7 @@ import (
"github.com/spf13/cobra"
"gitea.mynodes.xyz/ilker/llmgw/internal/agent/provision"
"gitea.mynodes.xyz/ilker/llmgw/internal/config"
"gitea.mynodes.xyz/ilker/llmgw/internal/control/adminapi"
"gitea.mynodes.xyz/ilker/llmgw/internal/onboard"
@@ -113,13 +114,14 @@ engines are kept.`,
f.StringVar(&na.opts.MgmtAddr, "mgmt-addr", "", "address engines are reached at (default: found by the agent)")
f.StringVar(&na.opts.MgmtIface, "mgmt-if", "", "interface NCCL bootstraps over (default: the one holding that address)")
f.StringVar(&na.opts.LlamaCppBin, "llamacpp-bin", "", "a llama-server you installed, instead of the one the agent installs")
f.StringVar(&na.opts.VLLMBin, "vllm-bin", "", "a vllm you installed; also set engines.vllm: \"\" in server.yaml")
f.StringVar(&na.opts.VLLMBin, "vllm-bin", "", "a vllm you installed, instead of the one the agent installs")
f.StringVar(&na.opts.SGLangPython, "sglang-python", "", "python of an SGLang virtualenv you installed")
f.StringVar(&na.opts.NvidiaSMI, "nvidia-smi", "", "where nvidia-smi is, when it is not on PATH")
f.StringVar(&na.opts.IBRoot, "ib-root", "", "the sysfs InfiniBand directory, when not /sys/class/infiniband")
f.StringVar(&na.opts.PKI, "pki", defaultPKIDir, "directory holding the certificate authority")
f.StringVar(&na.opts.Releases, "releases", "https://gitea.mynodes.xyz/ilker/llmgw/releases/download", "where release files are downloaded from")
f.BoolVar(&na.opts.IgnoreChecks, "ignore-checks", false, "add the node even when doctor finds a problem")
f.StringArrayVar(&na.opts.DisableEngines, "disable-engine", nil, "an engine this node never installs, e.g. vllm on GPUs it does not run on; repeatable")
f.StringVar(&na.admin, "admin", "", "the control plane's admin API, to watch the node join (default: from server.yaml, else 127.0.0.1:9090)")
f.StringVar(&na.serverCfg, "config", "/etc/llmgw/server.yaml", "the control plane's configuration, for the admin API's address")
f.BoolVar(&na.waitAll, "wait", false, "wait for every engine, vLLM included, not only llama.cpp")
@@ -148,6 +150,23 @@ func (na *nodeAdd) prepare() error {
}
}
}
for _, e := range o.DisableEngines {
if !slices.Contains(provision.Installable(), e) {
return fmt.Errorf("--disable-engine %s: the engines are %s", e, strings.Join(provision.Installable(), ", "))
}
}
// What the control plane will ask the node to install, so doctor checks
// that vLLM rather than its own default. Its overrides for a GPU class
// are not known until the node says what it has, and are not applied
// here; doctor's verdict on vLLM is a warning either way.
if o.VLLMVersion == "" {
if cfg, err := config.Load(na.serverCfg); err == nil {
o.VLLMVersion = cfg.WantedEngines()["vllm"]
if o.VLLMVersion == "" {
o.VLLMVersion = "none"
}
}
}
o.Version = version.Version
if o.Binary == "" {
exe, err := os.Executable()