TorchAO

license

BSD-3-Clause(OSI)

source

public

core-gated

ungated

BSD-3-Clause license body confirmed. The repository is public and unarchived and builds the whole product, and the README describes no paid tier, enterprise edition or license-gated build beside it, so source is public and the core ungated.

• https://github.com/pytorch/ao/blob/main/LICENSE recorded 2026-08-18

  LICENSE body read rather than trusting the GitHub label: it opens with Meta and Arm copyright lines and then runs the verbatim three-clause BSD text, which is why the API reports NOASSERTION.

• https://api.github.com/repos/pytorch/ao recorded 2026-08-18

  Repo metadata - license spdx_id NOASSERTION, private false, archived false, default branch main - for pytorch/ao.

• https://github.com/pytorch/ao/blob/main/README.md recorded 2026-08-18

  README describes PyTorch-native training-to-serving optimization with float8 and MX training, quantization-aware training, and int4 and int8 inference quantization, with measured speedups and memory savings quoted against unquantized baselines, with no paid tier, enterprise edition or license-key-gated build beside it.

4,080,208 PyPI downloads of `torchao` in the trailing 30 days, which lands in the 1M-10M band of the software usage scale, level 4.

• https://pypistats.org/api/packages/torchao/recent recorded 2026-08-18

  last_month downloads = 4,080,208 for torchao

Banded on the category feature matrix as multi-technique optimization toolchain. Placed one band below the apache-tvm anchor, on a matrix that bands on how much of the model-to-hardware transformation pipeline a product performs, over how many inputs and targets.

• https://github.com/pytorch/ao/blob/main/README.md recorded 2026-08-18

  README still documents PyTorch-native training-to-serving optimization with float8 and MX training, quantization-aware training, and int4 and int8 inference quantization, with measured speedups and memory savings quoted against unquantized baselines.