cellmap_flow.serving.client

Ask a running inference server about the model it is serving.

The dashboard runs wherever the jobs were launched from, which is frequently a node with no usable GPU – or, on LSF, one holding a single GPU in exclusive_process mode that something else already has a context on. Building the model there just to read its output shape is both wasteful and unreliable: for a script-defined model it means re-downloading weights and re-running torch.export, and it fails outright when a CUDA context cannot be created.

The inference server already loaded the model, on the node the job was actually submitted to. Ask it instead.

Attributes

logger
DEFAULT_TIMEOUT_SECONDS
GEOMETRY_FIELDS
OPTIONAL_FIELDS

Functions

fetch_model_info(→ dict)	Return the server's model info, or {"available": False, "reason": ...}.
model_geometry(info)	Pull the finetune tab's geometry out of a model_info payload.
running_job_host(model_name)	The host serving model_name, if a job for it is up.
geometry_stand_in(fields)	A stand-in for ModelConfig.config with the geometry in fields, or None.
model_geometry_config(model_name[, timeout])	The geometry of model_name's running server, as a geometry_stand_in.

Module Contents

cellmap_flow.serving.client.logger

cellmap_flow.serving.client.DEFAULT_TIMEOUT_SECONDS = 3

cellmap_flow.serving.client.fetch_model_info(host: str, timeout: float = DEFAULT_TIMEOUT_SECONDS) → dict

Return the server’s model info, or {"available": False, "reason": ...}.

Never raises: an unreachable server is an ordinary state here (the job may still be queued), not an error the caller should have to handle.

cellmap_flow.serving.client.model_geometry(info: dict)

Pull the finetune tab’s geometry out of a model_info payload.

Returns None when the payload has no geometry – an older server, which reported only the output activation.

cellmap_flow.serving.client.running_job_host(model_name)

The host serving model_name, if a job for it is up.

cellmap_flow.serving.client.GEOMETRY_FIELDS = ('read_shape', 'write_shape', 'input_voxel_size', 'output_voxel_size', 'output_channels')

cellmap_flow.serving.client.OPTIONAL_FIELDS = ('channels',)

cellmap_flow.serving.client.geometry_stand_in(fields)

A stand-in for ModelConfig.config with the geometry in fields, or None.

fields is a model_info payload or a geometry cache entry. The stand-in has the config’s attribute names, so callers that only read shapes and voxel sizes, and ModelGeometry.from_config, take it as the config. Every GEOMETRY_FIELDS entry, or nothing: callers use it as stand_in or model_config.config, and a SimpleNamespace missing one attribute is still truthy, so a partial answer would defeat the fallback and raise AttributeError deep in the caller instead.

cellmap_flow.serving.client.model_geometry_config(model_name, timeout=DEFAULT_TIMEOUT_SECONDS)

The geometry of model_name’s running server, as a geometry_stand_in.

None when no running server can answer, or an older one cannot report all of it, leaving the caller to fall back.