ai-hub (#3)

Reviewed-on: #3

src/qualcomm/aihub_jobs.py

@@ -0,0 +1,129 @@
+from pathlib import Path
+from typing import Any, TypedDict
+
+import qai_hub.hub as hub
+from qai_hub.client import CompileJob, Device, InferenceJob, Model, ProfileJob, QuantizeDtype, QuantizeJob
+
+
+class ModelJobResult(TypedDict):
+    job: CompileJob | QuantizeJob
+    job_id: str
+    model: Model
+    model_id: str
+
+
+class InferenceJobResult(TypedDict):
+    job: InferenceJob
+    job_id: str
+    outputs: Any
+
+
+class ProfileJobResult(TypedDict):
+    job: ProfileJob
+    job_id: str
+
+
+def _dataset_entries(inputs: dict[str, Any]) -> dict[str, list[Any]]:
+    return {name: value if isinstance(value, list) else [value] for name, value in inputs.items()}
+
+
+def submit_compile_job(
+    model: Any,
+    device_name: str,
+    input_specs: dict[str, tuple[tuple[int, ...], str]],
+    target_runtime: str,
+    options: str | None = None,
+    job_name: str | None = None,
+    model_name: str | None = None,
+) -> ModelJobResult:
+    compile_options = f"--target_runtime {target_runtime}"
+    if options:
+        compile_options = f"{compile_options} {options}"
+
+    model_arg = model
+    if isinstance(model, Path):
+        model_arg = str(model)
+    elif isinstance(model, str):
+        candidate = Path(model)
+        model_arg = model if candidate.exists() or candidate.suffix else hub.get_model(model)
+
+    if model_name and isinstance(model_arg, str) and Path(model_arg).exists():
+        model_arg = hub.upload_model(model_arg, name=model_name)
+
+    job = hub.submit_compile_job(
+        model=model_arg,
+        device=Device(device_name),
+        name=job_name,
+        input_specs=input_specs,
+        options=compile_options,
+    )
+    target_model = job.get_target_model()
+    if target_model is None:
+        raise RuntimeError(f"Compile job {job.job_id} did not produce a target model.")
+    return {"job": job, "job_id": str(job.job_id), "model": target_model, "model_id": str(target_model.model_id)}
+
+
+def submit_inference_job(
+    model_id: str,
+    device_name: str,
+    inputs: dict[str, Any],
+    output_dir: str | Path,
+    job_name: str | None = None,
+) -> InferenceJobResult:
+    job = hub.submit_inference_job(
+        model=hub.get_model(model_id),
+        device=Device(device_name),
+        inputs=_dataset_entries(inputs),
+        name=job_name,
+    )
+    out = Path(output_dir)
+    out.mkdir(parents=True, exist_ok=True)
+    data = job.download_output_data(str(out))
+    return {"job": job, "job_id": str(job.job_id), "outputs": data}
+
+
+def submit_profile_job(
+    model_id: str,
+    device_name: str,
+    options: str | None = None,
+    job_name: str | None = None,
+) -> ProfileJobResult:
+    job = hub.submit_profile_job(
+        model=hub.get_model(model_id),
+        device=Device(device_name),
+        name=job_name,
+        options=options or "",
+    )
+    return {"job": job, "job_id": str(job.job_id)}
+
+
+def submit_quantize_job(
+    model: str | Path,
+    calibration_data: dict[str, Any],
+    options: str | None = None,
+    job_name: str | None = None,
+    model_name: str | None = None,
+) -> ModelJobResult:
+    model_arg = str(model)
+    if model_name and Path(model_arg).exists():
+        model_arg = hub.upload_model(model_arg, name=model_name)
+    job = hub.submit_quantize_job(
+        model=model_arg,
+        calibration_data=_dataset_entries(calibration_data),
+        weights_dtype=QuantizeDtype.INT8,
+        activations_dtype=QuantizeDtype.INT8,
+        name=job_name,
+        options=options or "",
+    )
+    target_model = job.get_target_model()
+    if target_model is None:
+        raise RuntimeError(f"Quantize job {job.job_id} did not produce a target model.")
+    return {"job": job, "job_id": str(job.job_id), "model": target_model, "model_id": str(target_model.model_id)}
+
+
+def download_model(model_id: str, output_path: str | Path) -> str:
+    dest = Path(output_path)
+    dest.parent.mkdir(parents=True, exist_ok=True)
+    model = hub.get_model(model_id)
+    result = model.download(str(dest))
+    return str(result or dest)