Files
llmgw/internal/agent/discovery/host.go
T
Ilker ManapandClaude Opus 5.5 f5d6210b86 Install engines on any glibc system, with its own package manager
The llama.cpp build is published from Ubuntu but is not Ubuntu's in any way
that matters: it needs glibc 2.34 and GCC 12's libstdc++, which Debian 12
and RHEL 10 have and RHEL 9 does not. Refusing every system not called
"ubuntu" turned away the first two for their name. The build is now tried
everywhere, and ldd decides.

What ldd says is made readable. "/lib64/libstdc++.so.6: version
`GLIBCXX_3.4.30' not found" is a system too old for the build, and is
reported as "libstdc++.so.6 is too old (needs GLIBCXX_3.4.30)", once —
rather than as a missing library that is plainly installed.

Packages are named per family — libgomp1 for Debian's, libgomp for Red
Hat's — and installed with whichever of apt-get, dnf, yum or zypper the
machine has, decided from ID_LIKE rather than a list of distribution names.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-28 11:10:06 +02:00

155 lines
4.1 KiB
Go

package discovery
import (
"bufio"
"os"
"runtime"
"strings"
)
// Host is what a node is, as far as installing software on it is concerned.
type Host struct {
// OSID, OSVersion and OSCodename come from /etc/os-release: "ubuntu",
// "24.04", "noble".
OSID string `json:"os_id,omitempty"`
OSVersion string `json:"os_version,omitempty"`
OSCodename string `json:"os_codename,omitempty"`
// OSLike is ID_LIKE: the families this system says it follows, "debian"
// for Ubuntu, "rhel centos fedora" for Rocky. It is what decides the
// package manager, which the name alone does not for every derivative.
OSLike []string `json:"os_like,omitempty"`
// Arch is Debian's spelling, "amd64" or "arm64", because that is what
// package names and release archives are keyed by.
Arch string `json:"arch,omitempty"`
// CPUFlags are the vector extensions inference cares about, of those this
// processor has.
CPUFlags []string `json:"cpu_flags,omitempty"`
// NVIDIADriver is the loaded driver's version, empty when there is none.
NVIDIADriver string `json:"nvidia_driver,omitempty"`
}
// Family is the packaging family: "deb", "rpm", or "" when neither is known.
func (h Host) Family() string {
for _, id := range append([]string{h.OSID}, h.OSLike...) {
switch id {
case "debian", "ubuntu":
return "deb"
case "rhel", "fedora", "centos", "rocky", "almalinux", "suse", "opensuse":
return "rpm"
}
}
return ""
}
// HasCPUFlag reports whether the processor has an extension.
func (h Host) HasCPUFlag(f string) bool {
for _, have := range h.CPUFlags {
if have == f {
return true
}
}
return false
}
// interestingFlags are the extensions that decide which build of an engine
// runs well. A VM on QEMU's default CPU model has none of them — and still
// runs, five times slower, with nothing saying why.
var interestingFlags = []string{"avx", "avx2", "fma", "f16c", "avx512f", "avx512_bf16", "amx_tile", "asimd", "sve"}
// DiscoverHost reads what the machine is.
func DiscoverHost() Host {
h := hostFromOSRelease("/etc/os-release")
h.Arch = debianArch(runtime.GOARCH)
h.CPUFlags = cpuFlagsFrom("/proc/cpuinfo")
h.NVIDIADriver = nvidiaDriverFrom("/proc/driver/nvidia/version")
return h
}
func hostFromOSRelease(path string) Host {
var h Host
f, err := os.Open(path) //nolint:gosec // a fixed system path
if err != nil {
return h
}
defer f.Close()
sc := bufio.NewScanner(f)
for sc.Scan() {
k, v, ok := strings.Cut(sc.Text(), "=")
if !ok {
continue
}
v = strings.Trim(v, `"'`)
switch k {
case "ID":
h.OSID = v
case "VERSION_ID":
h.OSVersion = v
case "VERSION_CODENAME":
h.OSCodename = v
case "ID_LIKE":
h.OSLike = strings.Fields(v)
}
}
return h
}
func debianArch(goarch string) string {
switch goarch {
case "amd64", "arm64":
return goarch
case "386":
return "i386"
case "arm":
return "armhf"
}
return goarch
}
func cpuFlagsFrom(path string) []string {
b, err := os.ReadFile(path) //nolint:gosec // a fixed system path
if err != nil {
return nil
}
have := map[string]bool{}
for _, line := range strings.Split(string(b), "\n") {
k, v, ok := strings.Cut(line, ":")
if !ok {
continue
}
// "flags" on x86, "Features" on ARM. The first processor is enough:
// a machine does not mix instruction sets across its cores.
if k = strings.TrimSpace(k); k != "flags" && k != "Features" {
continue
}
for _, f := range strings.Fields(v) {
have[f] = true
}
break
}
var out []string
for _, f := range interestingFlags {
if have[f] {
out = append(out, f)
}
}
return out
}
// nvidiaDriverFrom reads the loaded kernel module's version, which exists
// exactly when a driver is loaded — unlike nvidia-smi, which can be installed
// on a machine whose module failed to load.
func nvidiaDriverFrom(path string) string {
b, err := os.ReadFile(path) //nolint:gosec // a fixed system path
if err != nil {
return ""
}
// "NVRM version: NVIDIA UNIX x86_64 Kernel Module 570.86.15 Thu ..."
fields := strings.Fields(string(b))
for i, f := range fields {
if f == "Module" && i+1 < len(fields) {
return fields[i+1]
}
}
return ""
}