Mobilint SDK qb Runtime Library : qbruntime

qbruntime is runtime library for Mobilint NPU products. Runtime Library is required to run inference on Mobilint NPUs using precompiled or custom models.

IMPORTANT: Please refer to official documentation for installing driver before using runtime library.

Prerequisites

Currently, pip installation is limited to below Ubuntu environments. For other environment, please refer to official documentation.

Ubuntu: 20.04 / 22.04 / 24.04
Python: 3.8 / 3.9 / 3.10 / 3.11 / 3.12
numpy

Installation

You may install python runtime library with following command

pip install mobilint-qb-runtime

For C++ library installation or downloading library from mobilint distribution site, please refer to official documentation.

Inference process

Running inference on Mobilint's NPU using the qbruntime runtime library involves four essential steps:

Initialize the NPU device.
Load the compiled model (MXQ file).
Upload model to the NPU device.
Run inference with user input.

Step 1: `Accelerator`

The Accelerator object represents the NPU device to be used. It abstracts a single device identified by the number appended to the device name (e.g., /dev/aries0 -> acc1, /dev/aries2 -> acc2). If no specific number is provided, NPU device 0 is used by default.

acc = qbruntime.Accelerator(0)

Step 2: `Model`

The Model object represents a model contained in an MXQ file. Upon creation, it immediately reads the MXQ file and stores the relevant information.

model = qbruntime.Model(MXQ_FILE_PATH)

Step 3: Pass `Model` information to the `Accelerator`

Pass the information with the {doxylink}mobilint::Model::launch(Accelerator & acc) method of Model object. It then uses the Accelerator object to run inference using this model.

Step 4: Run inference using passed `Model` information and input data

Get the input data and run inference using the mobilint::Model::infer() method of Model object.

model = qbruntime.Model(MXQ_FILE_PATH)
result = model.infer([INPUT])

Inference Scenario

## Python example
import qbruntime

MXQ_PATH = "path/to/mxq.mxq"

acc = qbruntime.Accelerator()               ## Step 1
model = qbruntime.Model(MXQ_PATH)           ## Step 2
model.launch(acc)                           ## Step 3

## Some preprocessing for input data

result = model.infer(preprocessed_input)    ## Step 4

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

mobilint_qb_runtime-1.3.1-cp314-cp314-win_amd64.whl (984.4 kB view details)

Uploaded Jul 10, 2026 CPython 3.14Windows x86-64

mobilint_qb_runtime-1.3.1-cp314-cp314-manylinux_2_31_x86_64.whl (1.5 MB view details)

Uploaded Jul 10, 2026 CPython 3.14manylinux: glibc 2.31+ x86-64

mobilint_qb_runtime-1.3.1-cp314-cp314-manylinux_2_28_aarch64.whl (1.2 MB view details)

Uploaded Jul 10, 2026 CPython 3.14manylinux: glibc 2.28+ ARM64

mobilint_qb_runtime-1.3.1-cp313-cp313-win_amd64.whl (957.3 kB view details)

Uploaded Jul 10, 2026 CPython 3.13Windows x86-64

mobilint_qb_runtime-1.3.1-cp313-cp313-manylinux_2_31_x86_64.whl (1.5 MB view details)

Uploaded Jul 10, 2026 CPython 3.13manylinux: glibc 2.31+ x86-64

mobilint_qb_runtime-1.3.1-cp313-cp313-manylinux_2_28_aarch64.whl (1.2 MB view details)

Uploaded Jul 10, 2026 CPython 3.13manylinux: glibc 2.28+ ARM64

mobilint_qb_runtime-1.3.1-cp312-cp312-win_amd64.whl (957.3 kB view details)

Uploaded Jul 10, 2026 CPython 3.12Windows x86-64

mobilint_qb_runtime-1.3.1-cp312-cp312-manylinux_2_31_x86_64.whl (1.5 MB view details)

Uploaded Jul 10, 2026 CPython 3.12manylinux: glibc 2.31+ x86-64

mobilint_qb_runtime-1.3.1-cp312-cp312-manylinux_2_28_aarch64.whl (1.2 MB view details)

Uploaded Jul 10, 2026 CPython 3.12manylinux: glibc 2.28+ ARM64

mobilint_qb_runtime-1.3.1-cp311-cp311-win_amd64.whl (956.0 kB view details)

Uploaded Jul 10, 2026 CPython 3.11Windows x86-64

mobilint_qb_runtime-1.3.1-cp311-cp311-manylinux_2_31_x86_64.whl (1.5 MB view details)

Uploaded Jul 10, 2026 CPython 3.11manylinux: glibc 2.31+ x86-64

mobilint_qb_runtime-1.3.1-cp311-cp311-manylinux_2_28_aarch64.whl (1.2 MB view details)

Uploaded Jul 10, 2026 CPython 3.11manylinux: glibc 2.28+ ARM64

mobilint_qb_runtime-1.3.1-cp310-cp310-win_amd64.whl (955.4 kB view details)

Uploaded Jul 10, 2026 CPython 3.10Windows x86-64

mobilint_qb_runtime-1.3.1-cp310-cp310-manylinux_2_31_x86_64.whl (1.5 MB view details)

Uploaded Jul 10, 2026 CPython 3.10manylinux: glibc 2.31+ x86-64

mobilint_qb_runtime-1.3.1-cp310-cp310-manylinux_2_28_aarch64.whl (1.2 MB view details)

Uploaded Jul 10, 2026 CPython 3.10manylinux: glibc 2.28+ ARM64

mobilint_qb_runtime-1.3.1-cp39-cp39-win_amd64.whl (947.3 kB view details)

Uploaded Jul 10, 2026 CPython 3.9Windows x86-64

mobilint_qb_runtime-1.3.1-cp39-cp39-manylinux_2_31_x86_64.whl (1.5 MB view details)

Uploaded Jul 10, 2026 CPython 3.9manylinux: glibc 2.31+ x86-64

mobilint_qb_runtime-1.3.1-cp39-cp39-manylinux_2_28_aarch64.whl (1.2 MB view details)

Uploaded Jul 10, 2026 CPython 3.9manylinux: glibc 2.28+ ARM64

mobilint_qb_runtime-1.3.1-cp38-cp38-win_amd64.whl (955.4 kB view details)

Uploaded Jul 10, 2026 CPython 3.8Windows x86-64

mobilint_qb_runtime-1.3.1-cp38-cp38-manylinux_2_31_x86_64.whl (1.5 MB view details)

Uploaded Jul 10, 2026 CPython 3.8manylinux: glibc 2.31+ x86-64

mobilint_qb_runtime-1.3.1-cp38-cp38-manylinux_2_28_aarch64.whl (1.2 MB view details)

Uploaded Jul 10, 2026 CPython 3.8manylinux: glibc 2.28+ ARM64

File details

Details for the file mobilint_qb_runtime-1.3.1-cp314-cp314-win_amd64.whl.

File metadata

Download URL: mobilint_qb_runtime-1.3.1-cp314-cp314-win_amd64.whl
Upload date: Jul 10, 2026
Size: 984.4 kB
Tags: CPython 3.14, Windows x86-64
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.2.0 CPython/3.12.10

File hashes

Hashes for mobilint_qb_runtime-1.3.1-cp314-cp314-win_amd64.whl
Algorithm	Hash digest
SHA256	`7ad219726e611904f1a9b33260467d7a1880f968d24dae39d8ba9cca986722d2`
MD5	`2ef19f21ac68393ba458ee4494a59265`
BLAKE2b-256	`d434f939573c468ea63bac4a5eff0456cb0107ce2301c40ad4121fd116c8808b`

Algorithm	Hash digest
SHA256	`99e203549b16699005271069cf865b78ddfb56c96fd9b99d18ecb839555099d9`
MD5	`cb678105eb30d9a37aac451a9681c846`
BLAKE2b-256	`f674264db15c284c0ad7e1f02d9a0c4cbcc27f567528f4af432747b9749341fc`

Algorithm	Hash digest
SHA256	`7fb35cdef925012cb057af815e6e9a824f528fbc856d75460adcc40ed3ab4e49`
MD5	`e12b97e771b75ca13dc08d199332a22e`
BLAKE2b-256	`b6ad335df290953172013b7a2b36aafec0338358671c7d6e6f85e32daf590fb8`

Algorithm	Hash digest
SHA256	`80ebd6139f59a6de16023fbd3bfd56a19f989e24eb0bae9c0a4a8933e1fa66d8`
MD5	`68003de29889dabe2c0522f5b5ad2b31`
BLAKE2b-256	`7ae8f4c067723fb323b319e5e6396934099ff91f8836b7a2372b073ffee8a2cf`

Algorithm	Hash digest
SHA256	`2be984f0ab7fe051533b344568ad0815e413fbdeedf26c95dfb4c0b400a5d8fc`
MD5	`580238b9b6b609d184903f0a131f8788`
BLAKE2b-256	`d3420ad5fb9404b94de39db7d3d658bf8670211178f060bd38070ea4727079ed`

Algorithm	Hash digest
SHA256	`83ea4bbab7f40661e9d978a8724358aeb54a2d2207176d0ac16004d5d9c06cff`
MD5	`a7f01407c2915195f124805f9123534d`
BLAKE2b-256	`0ea6a1c7a2744e855fe39b81d3ff759aeec97fd008a398681b7941cc1e3149ac`

Algorithm	Hash digest
SHA256	`605f985737fc1fbb56cd38551f5d1721bdd01c9ee16672e109bfd239481a5bb3`
MD5	`69a451e98578cd7ddf1d998a3dc0b522`
BLAKE2b-256	`e65f965bab7380e4d1e1b26828bf21c5799f6b71eab7e7cd17e18db3244b8306`

Algorithm	Hash digest
SHA256	`83adc29ea9ef0387f0be39e879e0015321f177e45df0d2822006e97ea443f6e6`
MD5	`b7e717fd4735e1647c46f3d2615a66fa`
BLAKE2b-256	`80de23fbf32171abfb07bb856ff6ff81bd3dec14250a24168bf4ab394ae3ed5a`

Algorithm	Hash digest
SHA256	`2da6b0cdc70427a4a846639a58d89a66486fa73a83b1938beb9bdbbebd44700a`
MD5	`68f522e508da23e99dd6f2d1d9bc37a2`
BLAKE2b-256	`ea177070196db14eb85b5444b31c5e5f7f69b3e63a4c3d2b8f955a65136e211a`

Algorithm	Hash digest
SHA256	`558dbaa9f9bff34f150190046aef05276fae9e1cb606271c34db827f8dc696e9`
MD5	`0cae38eaa03422e841bc582831640144`
BLAKE2b-256	`880b34fe7ff9df8efa8a00f661b430ac5dccd2952d820265387c605f473c9a5f`

Algorithm	Hash digest
SHA256	`14cd69f71a4923f02c7c5c1360859f2d6b371d55a48e21534a96ddd8c14e6677`
MD5	`0b196c1a1da58469f96a6e19cd0aa496`
BLAKE2b-256	`8a0ab59af0b2b45285098a7bba3abd7323a2f3f53c4b20449f0a9b3d7ba06137`

Algorithm	Hash digest
SHA256	`ba4b1ddaf05138d0713b553ce02e23355496d527dcfd68ba2cb70fbcfbef6caa`
MD5	`5e30430527f6f013db0171a125003772`
BLAKE2b-256	`f45d00d6a33309ed9dff1092657ba6aa870e4199cc9a842c0921dc2640f8a424`

Algorithm	Hash digest
SHA256	`69695fe8a8969724e9c92dcc7dfb05caa43ada4e3aecbae40f70f458d5e08344`
MD5	`ad2c5db437482a1ceef5aa19786ff0d4`
BLAKE2b-256	`2894a2efa25cdc821aa1255416d53cb3f49c01cd8054ca46b8136458862514a7`

Algorithm	Hash digest
SHA256	`e9a2259d26b2f02bcd237e774adee3cee41cc2a330b9eafec78b5af37f7a7e5d`
MD5	`695890b513471e52802f88818f3b84d5`
BLAKE2b-256	`5032ec80e0491d08b8e8d3d4c494c2528333ba45cbee74204c173600e7cb0bb6`

Algorithm	Hash digest
SHA256	`ee039a3ee0ebae650e3396f75479be33e45cc077925f7a299401d0ab50eb03c4`
MD5	`66ff5b7b308f81865dbf16b5409d0cad`
BLAKE2b-256	`b9d81557203ba74038449bd1959c9237ed0774709b3b5a129cd2082f33dabf5a`

Algorithm	Hash digest
SHA256	`9784403a9f15a3679b078c2e27c49e495ccfff0e8114065eae1ac5c6f07f2593`
MD5	`a71577ad2aafa0c5c1e91ab245868b78`
BLAKE2b-256	`616d29d7ecad37f95bceaad8ab434e8761308dcbb88aa76d00c30800e9bd596a`

Algorithm	Hash digest
SHA256	`1c4c050d5e883958fc4fca78bd55cb9cf16cc3d8d649a847348a0806ea3ad8e8`
MD5	`38456213ec36c8732262eccdec04f6fd`
BLAKE2b-256	`88d20373ce090e2391ddbde08d8c803fbed925b4a210cd81a87a94e6f83c3d14`

Algorithm	Hash digest
SHA256	`c936b68cf4d45ed90283cb3ee3bdd68e6aa8331a04b702c381a52988e63cac16`
MD5	`6d0f0cf521b6bc2a6d879efffe251719`
BLAKE2b-256	`a32080177ce7ec5894151a25893c5ca01078402b016a2777e6316fa35d7586ff`

Algorithm	Hash digest
SHA256	`c9902dc7c10f2086ccf24e6fcddb2be77dbaa111ae733d1190bba93dd5f1e7b1`
MD5	`4131e29f7fa04d0cc18e43b5e101be6f`
BLAKE2b-256	`2760dfb97b95f8e4338ba69941a44d0bd37fd76802d1fb05d2aeb6117356cddf`

Algorithm	Hash digest
SHA256	`c58457ac1f46e63382926424136d86f1b2d1721a867a2da3eeb1f2ea5217c98d`
MD5	`bef4d3f82dc2c7845cb43096cc2face7`
BLAKE2b-256	`7d2951d6cf39a03d3e1c1c1b2f7413f1f035041e41ae7caafa7d47bed28f6b58`

Algorithm	Hash digest
SHA256	`48e0327eef51231fa4109b1da20da96acc32f35eaefe5ee89102d4ba0d3793de`
MD5	`7e20d470da974d18f942e2dedf65f526`
BLAKE2b-256	`95420ffc53427384590bd1cf6c2602fe49b59d6b49eaa446d42d0c3fad5936fc`

mobilint-qb-runtime 1.3.1

Mobilint SDK qb Runtime Library : qbruntime

Prerequisites

Installation

Inference process

Step 1: Accelerator

Step 2: Model

Step 3: Pass Model information to the Accelerator

Step 4: Run inference using passed Model information and input data

Inference Scenario

Project links

Key dates

1 maintainer

Credits

Tags

Classifiers

Download files

Source Distributions

Built Distributions

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

Step 1: `Accelerator`

Step 2: `Model`

Step 3: Pass `Model` information to the `Accelerator`

Step 4: Run inference using passed `Model` information and input data