Skip to content

CLI reference ​

Inclavate installs three programs:

ProgramWhat it does
dppanThe command you use: download models, join a node, run a model locally, start the dashboard
dppan-orchestratorThe server that takes requests and sends work to nodes. Its flags are all settings
dppan-nodeThe node server. dppan join starts and registers one for you; you rarely run it yourself

Every program also takes --help, --version and --no-banner (or INCLAVATE_NO_BANNER=1) to hide the startup banner.

dppan ​

dppan [OPTIONS] <COMMAND>
OptionDefault
--log-levelwarntrace, debug, info, warn or error. Also LOG_LEVEL
--config <FILE>~/.dppan/config.tomlWhere dppan keeps its settings, such as the orchestrator dppan join last used
Command
joinJoin the network as a node
pullDownload a model, or part of one
runRun a model on this machine alone, with no orchestrator
uiStart the dashboard
statusShow the orchestrator and its nodes
modelsList the model catalogs and what is installed
downloadDownload a model through Ollama
manifestMake a per-tensor integrity manifest from a full model file
benchMeasure this machine's speed
updateUpdate to the latest release
uninstallRemove the install and its PATH entry

dppan join ​

dppan join --orchestrator <URL> [OPTIONS]
FlagEnvDefault
--orchestratorORCHESTRATOR_URLrequiredOrchestrator URL, e.g. http://192.168.1.10:8001
--model, -mDPPAN_MODELllama3.2:1bOllama model name or path to a .gguf file. With --visual and no --model, the node serves no text model
--ggufGGUF_PATHnoneA model file already downloaded (a full file or a dppan pull shard); skips Ollama. --model stays the id it registers with
--layersautoLayer range to serve, inclusive both ends like pull (e.g. 0-15 = 16 layers). A shard defaults to its own range
--visualoffAlso offer this machine's image and video models: see Image and video nodes
--namefrom device, model and layersA name for this node, shown in the dashboard
--deviceautoauto, metal, cuda or cpu
--gateway-urlGATEWAY_URLthe orchestrator's host, port + 1000Where to dial the orchestrator's gateway, e.g. http://orch:9001
--portPORT5001The node's HTTP port
--grpc-portGRPC_PORT5002The node's gRPC port
--legacyoffListen on inbound ports instead of dialling the orchestrator; those ports must then be reachable
--http-url, --grpc-urlhttp://localhost:<port>The addresses other machines use to reach this node's ports

A node joins through the orchestrator's gateway and needs no inbound ports. dppan join remembers the orchestrator in ~/.dppan/config.toml, so dppan status and dppan ui find it without --orchestrator.

dppan pull ​

dppan pull <MODEL> [OPTIONS]
FlagDefault
<MODEL>requiredllama3.3:70b (Ollama) · hf:owner/repo[:QUANT] · inclavate:slug
--layersallLayer range to download, inclusive (e.g. 0-26): see Sharded download
--orchoffInclude the orchestrator's tensors, and download a published projector
--projector-onlyoffDownload only the orchestrator's projector
--projector <FILE>autoPick an exact projector instead of the automatic F16, then BF16
--projector-out <PATH>model storeWhere to write the projector
--allow-unverified-projectoroffAccept a projector whose source publishes no SHA-256, skipping that check
--out, -o~/.dppan/models/…Where to write the shard, or the model's directory for speech and music
--verifyoffCheck every tensor's SHA-256 against the integrity manifest
--manifestautoManifest file or URL for --verify
--remoteoffFetch byte ranges even when the full file is already here
--speechoffPull a speech model: a backbone and its audio decoder. For a repository that publishes a PyTorch checkpoint, this converts it: see Speech › Getting a model
--speech-decoder <MODEL>Where the speech decoder lives, when it is not published beside the backbone
--f5-variant <v0|v1>Which generation an F5-TTS model is, when nothing else says
--component <ROLE>Pull one part of a model published as several files. Music models are assembled this way: see Music › Getting a music model
--f16offStore an unquantised component's F32 tensors as F16: half the size, roughly half the generation time. Lossy, so opt-in
--visualoffInstall an image or video model from the catalog by its id, e.g. dppan pull --visual z-image-turbo: see Images › Getting an image or video model
--from <DIR>With --visual: look in this folder first, and link in any file whose size and SHA-256 match instead of downloading it. Repeatable

For speech and music models, pass --out and point every component of one model at the same directory: that directory is the model. Projectors are kept only on the orchestrator, under ~/.dppan/models/projectors/<model-id>/; a projector written elsewhere with --projector-out needs projector_path in that model's config/models.toml entry.

dppan run ​

dppan run [OPTIONS]

Runs a whole model on this machine, with no orchestrator: interactive, or one prompt with --prompt.

FlagDefault
--model, -mllama3.2:1bOllama model name or path to a .gguf file. Also DPPAN_MODEL
--prompt, -pAnswer one prompt, then exit
--max-tokens512Most tokens to generate
--temperature0.7Sampling temperature; 0 always picks the likeliest token
--top-p0.9Nucleus sampling threshold
--deviceautoauto, metal, cuda or cpu
--think, --no-thinkthe model's ownTurn a thinking model's reasoning on or off
--reasoning-effort <LEVEL>How hard to think: none, low, medium, high, as the model allows
--image <PATH>Attach an image. Repeatable
--audio <PATH>Attach a WAV or MP3 file. Repeatable
--video-frames <PATH@MS>Attach one video frame and its time in milliseconds. Repeatable, in order
--projector <FILE>the one pull downloadedUse this projector instead

More: Chat › From the command line.

dppan ui ​

FlagDefault
--orchestratorORCHESTRATOR_URL, then the one dppan join rememberedOrchestrator URL
--port3000Dashboard port
--host127.0.0.1Bind address: 0.0.0.0 opens it to your network
--openoffOpen the browser once it is up

dppan status ​

FlagDefault
--orchestratorORCHESTRATOR_URL, then the one dppan join rememberedOrchestrator URL
--watch, -w0Refresh every N seconds; 0 prints once

dppan models ​

Lists the curated catalog, and which models are already here.

Flag
--ttsList speech models instead of text models
--musicList music models
--visualList image and video models
--jsonPrint the catalog as JSON

dppan download ​

dppan download <MODEL> [--force]

Downloads a model through Ollama, e.g. llama3.2:1b. --force downloads it again even if it is already here.

dppan manifest ​

dppan manifest <GGUF> [--out <FILE>]

Makes a per-tensor integrity manifest from a full model file, or a local Ollama model id, for --verify. Prints it, or writes it to --out.

dppan bench ​

FlagDefault
--model, -mllama3.2:1bModel to measure with
--steps32Decode steps to run

dppan update ​

Flag
--version <VERSION>Install this version instead of the latest, e.g. v0.8.5
--forceReinstall even if already on the latest

dppan uninstall ​

--yes (-y) skips the confirmation prompt.

dppan-orchestrator ​

dppan-orchestrator --port 8001 [OPTIONS]

Every flag is also an environment variable, and every one is listed in Configuration. The ones most setups use:

FlagEnvDefault
--portPORTrequiredREST API port
--admin-tokenDPPAN_ADMIN_TOKENnoneTurns on admin endpoints and the dashboard's Admin tab
--models-configDPPAN_MODELS_CONFIGconfig/models.toml (the current directory, else next to the binary)The model registry
--log-levelLOG_LEVELinfotrace, debug, info, warn or error

dppan-node ​

dppan join starts and registers a node for you. Run dppan-node yourself only to serve a fixed range of a model file:

FlagEnvDefault
--gguf-pathGGUF_PATHrequiredThe model file
--start-layerSTART_LAYER0First layer served, inclusive
--end-layerEND_LAYERrequiredOne past the last layer served
--orchestrator-urlORCHESTRATOR_URLnone (runs alone)Orchestrator to register with
--model-idMODEL_IDnoneThe model id to register with, e.g. llama3.2:1b
--deviceDEVICEautoauto, metal, cuda or cpu
--portPORT5001HTTP port
--grpc-portGRPC_PORT5002gRPC port
--node-idNODE_IDgeneratedNode id
--http-url, --grpc-urlHTTP_URL, GRPC_URLhttp://localhost:<port>The addresses other machines use to reach this node

Free to run · Proprietary