mirror of
https://github.com/mudler/LocalAI.git
synced 2025-05-20 02:24:59 +00:00
feat: add machine tag and inference timings (#4577)
* Add machine tag option, add extraUsage option, grpc-server -> proto -> endpoint extraUsage data is broken for now Signed-off-by: mintyleaf <mintyleafdev@gmail.com> * remove redurant timing fields, fix not working timings output Signed-off-by: mintyleaf <mintyleafdev@gmail.com> * use middleware for Machine-Tag only if tag is specified Signed-off-by: mintyleaf <mintyleafdev@gmail.com> --------- Signed-off-by: mintyleaf <mintyleafdev@gmail.com>
This commit is contained in:
parent
8027fdf1c7
commit
96f8ec0402
15 changed files with 137 additions and 48 deletions
|
@ -70,6 +70,7 @@ type RunCMD struct {
|
|||
WatchdogBusyTimeout string `env:"LOCALAI_WATCHDOG_BUSY_TIMEOUT,WATCHDOG_BUSY_TIMEOUT" default:"5m" help:"Threshold beyond which a busy backend should be stopped" group:"backends"`
|
||||
Federated bool `env:"LOCALAI_FEDERATED,FEDERATED" help:"Enable federated instance" group:"federated"`
|
||||
DisableGalleryEndpoint bool `env:"LOCALAI_DISABLE_GALLERY_ENDPOINT,DISABLE_GALLERY_ENDPOINT" help:"Disable the gallery endpoints" group:"api"`
|
||||
MachineTag string `env:"LOCALAI_MACHINE_TAG" help:"Add Machine-Tag header to each response which is useful to track the machine in the P2P network" group:"api"`
|
||||
LoadToMemory []string `env:"LOCALAI_LOAD_TO_MEMORY,LOAD_TO_MEMORY" help:"A list of models to load into memory at startup" group:"models"`
|
||||
}
|
||||
|
||||
|
@ -107,6 +108,7 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
|
|||
config.WithHttpGetExemptedEndpoints(r.HttpGetExemptedEndpoints),
|
||||
config.WithP2PNetworkID(r.Peer2PeerNetworkID),
|
||||
config.WithLoadToMemory(r.LoadToMemory),
|
||||
config.WithMachineTag(r.MachineTag),
|
||||
}
|
||||
|
||||
if r.DisableMetricsEndpoint {
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue