mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-28 09:05:05 -04:00
* feat(system): report per-model DRM VRAM Expose optional resident device memory for local backend process trees. Deduplicate DRM clients and omit unsupported or incomplete readings. Document accounting limits and preserve a measured zero in JSON. Closes #11970. Assisted-by: Codex:gpt-6 * fix(system): document trusted procfs reads Scope G304 annotations to paths built from the fixed procfs root, integer process IDs, and kernel directory entries. These reads accept no user-controlled path components. Assisted-by: Codex:GPT-6 gosec --------- Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
78 lines
2.3 KiB
Go
78 lines
2.3 KiB
Go
package localai
|
|
|
|
import (
|
|
"strconv"
|
|
|
|
"github.com/labstack/echo/v4"
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/schema"
|
|
"github.com/mudler/LocalAI/core/services/monitoring"
|
|
"github.com/mudler/LocalAI/pkg/model"
|
|
"github.com/mudler/LocalAI/pkg/xsysinfo"
|
|
)
|
|
|
|
// SystemInformations returns the system informations
|
|
// @Summary Show the LocalAI instance information
|
|
// @Tags monitoring
|
|
// @Success 200 {object} schema.SystemInformationResponse "Response"
|
|
// @Router /system [get]
|
|
func SystemInformations(cl *config.ModelConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig, sampler *monitoring.LocalProcessSampler) echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
availableBackends := []string{}
|
|
loadedModels := ml.ListLoadedModels()
|
|
for b := range appConfig.ExternalGRPCBackends {
|
|
availableBackends = append(availableBackends, b)
|
|
}
|
|
for b := range ml.GetAllExternalBackends(nil) {
|
|
availableBackends = append(availableBackends, b)
|
|
}
|
|
|
|
sysmodels := []schema.SysInfoModel{}
|
|
live := map[int32]struct{}{}
|
|
for _, m := range loadedModels {
|
|
entry := schema.SysInfoModel{ID: m.ID}
|
|
// The loader tracks only the ID. Which engine is serving a model is
|
|
// the first thing an operator wants beside its name, and it is one
|
|
// config lookup away.
|
|
if cfg, ok := cl.GetModelConfig(m.ID); ok {
|
|
entry.Backend = cfg.Backend
|
|
}
|
|
if pid, ok := localPID(m); ok && sampler != nil {
|
|
live[pid] = struct{}{}
|
|
if proc, err := sampler.Sample(pid); err == nil {
|
|
entry.Process = proc
|
|
}
|
|
}
|
|
if pid, ok := localPID(m); ok {
|
|
if used, ok := xsysinfo.ProcessVRAM(int(pid)); ok {
|
|
entry.SizeVRAM = &used
|
|
}
|
|
}
|
|
sysmodels = append(sysmodels, entry)
|
|
}
|
|
if sampler != nil {
|
|
sampler.Retain(live)
|
|
}
|
|
return c.JSON(200,
|
|
schema.SystemInformationResponse{
|
|
Backends: availableBackends,
|
|
Models: sysmodels,
|
|
},
|
|
)
|
|
}
|
|
}
|
|
|
|
// localPID is the PID of the backend process this host started for m. A model
|
|
// served by a remote worker, or through an external gRPC address, has none.
|
|
func localPID(m *model.Model) (int32, bool) {
|
|
p := m.Process()
|
|
if p == nil {
|
|
return 0, false
|
|
}
|
|
pid, err := strconv.ParseInt(p.CurrentPID(), 10, 32)
|
|
if err != nil || pid <= 0 {
|
|
return 0, false
|
|
}
|
|
return int32(pid), true
|
|
}
|