mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-31 10:28:43 -04:00
8cec22c3b7
* feat(vram): add vrambudget primitive for per-node VRAM caps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): apply default VRAM budget in xsysinfo aggregate getters Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): wire LOCALAI_VRAM_BUDGET flag to xsysinfo default budget Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): persist VRAM budget via runtime settings with live apply Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(vram): reset process-global VRAM budget after runtime-settings spec Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): add VRAM budget field to Settings page Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): store and enforce per-node VRAM budget in the node registry Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): apply per-node VRAM budget in router hardware defaults Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): report worker VRAM budget in node registration The distributed worker now reports its operator-set VRAM budget string (LOCALAI_VRAM_BUDGET) to the server on registration. The worker keeps reporting RAW total/available VRAM and never sets the xsysinfo process-global budget (that stays standalone-only); the server resolves and enforces the budget uniformly (Task 6). Also closes a Task 6 gap: on re-registration, a struct Updates zero-skips an empty budget, so a worker that dropped LOCALAI_VRAM_BUDGET left the stale cap in place. For non-admin-override nodes the budget columns are now force-written (map Updates) even when empty, so removing the env var clears the cap; admin overrides are preserved unchanged. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * style(vram): drop em dash from worker-clear comment Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): add node VRAM budget admin endpoints Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): add node VRAM budget control to the node UI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): expose set_node_vram_budget MCP admin tool Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(vram): document LOCALAI_VRAM_BUDGET and node VRAM budget UI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(vram): avoid double-applying VRAM budget in GetResourceAggregateInfo The GPU-branch aggregate returned by GetResourceInfo is sourced from GetGPUAggregateInfo, which already caps total/free/used against the process-wide VRAM budget. GetResourceAggregateInfo then applied the budget a second time. For an absolute budget this is idempotent, but for a percentage budget b.Apply resolves the ceiling as a fraction of its input total, so a second pass yields P*(P*T) instead of P*T and distorts UsagePercent (read by the memory reclaimer in pkg/model/watchdog.go). Remove the redundant second application so the budget is applied exactly once, against the raw physical totals, upstream in GetGPUAggregateInfo. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(vram): implement SetNodeVRAMBudget on mcp assistant test stub The LocalAIClient interface gained SetNodeVRAMBudget; the stubClient in core/http/endpoints/mcp used by the assistant tests is a separate implementer and needs the method too (broke golangci-lint typecheck and both test jobs). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
69 lines
2.2 KiB
Go
69 lines
2.2 KiB
Go
package httpapi
|
|
|
|
import (
|
|
"fmt"
|
|
"net/url"
|
|
)
|
|
|
|
// Route paths for the LocalAI admin REST surface that this client targets.
|
|
// Static paths are constants; dynamic paths are builders that handle
|
|
// url.PathEscape on segment values. Keep these aligned with the server-side
|
|
// registrations in core/http/routes/localai.go — the Tool↔REST drift detector
|
|
// in coverage_test.go documents the mapping.
|
|
const (
|
|
routeWelcome = "/"
|
|
routeModelsApply = "/models/apply"
|
|
routeModelsAvail = "/models/available"
|
|
routeModelsGall = "/models/galleries"
|
|
routeModelsImport = "/models/import-uri"
|
|
routeModelImport = "/models/import"
|
|
routeAliases = "/api/aliases"
|
|
routeModelsReload = "/models/reload"
|
|
routeBackendLoad = "/backend/load"
|
|
routeBackends = "/backends"
|
|
routeBackendsKnown = "/backends/known"
|
|
routeBackendsApply = "/backends/apply"
|
|
routeNodes = "/api/nodes"
|
|
routeVRAMEstimate = "/api/models/vram-estimate"
|
|
routeBranding = "/api/branding"
|
|
routeSettings = "/api/settings"
|
|
routeUsage = "/api/usage"
|
|
routeUsageAll = "/api/usage/all"
|
|
routePIIEvents = "/api/pii/events"
|
|
routeMiddleware = "/api/middleware/status"
|
|
routeRouterDecisions = "/api/router/decisions"
|
|
routeVoiceProfiles = "/api/voice-profiles"
|
|
)
|
|
|
|
func routeJobStatus(jobID string) string {
|
|
return "/models/jobs/" + url.PathEscape(jobID)
|
|
}
|
|
|
|
func routeModelDelete(name string) string {
|
|
return "/models/delete/" + url.PathEscape(name)
|
|
}
|
|
|
|
func routeModelConfigJSON(name string) string {
|
|
return "/api/models/config-json/" + url.PathEscape(name)
|
|
}
|
|
|
|
func routeBackendUpgrade(name string) string {
|
|
return "/backends/upgrade/" + url.PathEscape(name)
|
|
}
|
|
|
|
func routeToggleModelState(name, action string) string {
|
|
return fmt.Sprintf("/models/toggle-state/%s/%s", url.PathEscape(name), url.PathEscape(action))
|
|
}
|
|
|
|
func routeToggleModelPinned(name, action string) string {
|
|
return fmt.Sprintf("/models/toggle-pinned/%s/%s", url.PathEscape(name), url.PathEscape(action))
|
|
}
|
|
|
|
func routeVoiceProfileDelete(id string) string {
|
|
return "/api/voice-profiles/" + url.PathEscape(id)
|
|
}
|
|
|
|
func routeNodeVRAMBudget(id string) string {
|
|
return "/api/nodes/" + url.PathEscape(id) + "/vram-budget"
|
|
}
|