qbruntime.accelerator.Accelerator Class Reference

SDK qb Runtime Library v1.4 MCS001-KR

• qbruntime
• accelerator
• Accelerator

Public Member Functions | Protected Attributes | List of all members

qbruntime.accelerator.Accelerator Class Reference

Python API Reference

Represents an accelerator, i.e., an NPU, used for executing models. More...

Public Member Functions
	__init__ (self, int dev_no=0)
	__init__ (self, str device_name="auto")
	__init__ (self, str device_name="auto", int dev_no=0)
	__init__ (self, device_name="auto", dev_no=0)
	Creates an Accelerator object for a specific target device and device number.
str	get_device_name (self)
	Returns the resolved device name of this accelerator.
PinnedMemory	allocate_pinned_memory (self, Sequence[int] shape, np.dtype dtype)
	Allocates an NPU-accessible pinned memory buffer.

Protected Attributes
	_accelerator = _cQbRuntime.Accelerator(device_name, dev_no)

Detailed Description

Represents an accelerator, i.e., an NPU, used for executing models.

Attention

For the regulus-usb device family, do not unplug the USB device while the runtime is running. Disconnecting a device that is in use may crash the program or cause unexpected misbehavior.

Definition at line 17 of file accelerator.py.

Constructor & Destructor Documentation

◆ __init__() [1/4]

qbruntime.accelerator.Accelerator.__init__	(		self,
		int	dev_no = 0 )

Definition at line 27 of file accelerator.py.

◆ __init__() [2/4]

qbruntime.accelerator.Accelerator.__init__	(		self,
		str	device_name = "auto" )

Definition at line 30 of file accelerator.py.

◆ __init__() [3/4]

qbruntime.accelerator.Accelerator.__init__	(		self,
		str	device_name = "auto",
		int	dev_no = 0 )

Definition at line 33 of file accelerator.py.

◆ __init__() [4/4]

qbruntime.accelerator.Accelerator.__init__	(		self,
			device_name = "auto",
			dev_no = 0 )

Creates an Accelerator object for a specific target device and device number.

The device_name parameter selects target device to open; case-insensitive. Supported values:

• "auto"
• "aries", "aries-rb"
• "regulus", "regulus-usb"
• "regulus-ra", "regulus-ra-usb"
• "regulus-rb", "regulus-rb-usb"

Automatic resolution:

• "auto" resolves the target device automatically, but only when exactly one supported kind of target device is present in the system.
• A base name ("aries", "regulus", "regulus-usb", ...) is a shorthand for every target device whose name begins with it (e.g. "aries" matches "aries-rb"). It resolves to the concrete target device automatically, but only when exactly one such matching target device is present.

The dev_no parameter is the device number. For example, on Linux an ARIES NPU attached as /dev/aries0 has device number 0.

Parameters

[in]	device_name	Device name to open (case-insensitive). See the list above.
[in]	dev_no	The device number to associate with the Accelerator.

Exceptions

QbRuntimeError

If device_name is unknown, if auto-resolution is ambiguous (more than one candidate), or if no matching device exists.

Note

Supported constructor forms:

• Accelerator(): auto-select the only attached NPU.
• Accelerator(dev_no): auto-detect device, open target device dev_no.
• Accelerator(device_name): open device_name at device 0.
• Accelerator(device_name, dev_no): open device_name at device dev_no.

Definition at line 35 of file accelerator.py.

Member Function Documentation

◆ get_device_name()

str qbruntime.accelerator.Accelerator.get_device_name

(

self

)

Returns the resolved device name of this accelerator.

When created with a automatic resolve such as "auto", "aries", this returns the real target device name that was resolved (e.g. "aries-rb", "regulus-ra-usb").

Returns

The resolved device name.

Definition at line 74 of file accelerator.py.

◆ allocate_pinned_memory()

PinnedMemory qbruntime.accelerator.Accelerator.allocate_pinned_memory	(		self,
		Sequence[int]	shape,
		np.dtype	dtype )

Allocates an NPU-accessible pinned memory buffer.

The returned buffer can be used as input or output for zero-copy inference via Model.infer_pinned_memory.

Note

This is an experimental API and is only supported on REGULUS device.

Parameters

shape	The shape of the buffer to allocate.
dtype	The element type of the buffer. Must be numpy.float32 or numpy.uint8.

Returns

A PinnedMemory wrapping the allocated buffer.

Definition at line 86 of file accelerator.py.

Member Data Documentation

◆ _accelerator

qbruntime.accelerator.Accelerator._accelerator = _cQbRuntime.Accelerator(device_name, dev_no)

protected

Definition at line 72 of file accelerator.py.

---

The documentation for this class was generated from the following file:

• accelerator.py

---

Generated by  1.14.0