tosa-tools
TOSA Tools: serialization library, reference model, optional MLIR translator
Decision gist · record as of 2026-08-14
Yes, if you are working with TOSA in a compiler, ML framework, or operator validation context. The package is actively maintained, permissively licensed, supports current Python versions, and has no known vulnerabilities. Install friction is moderate due to native compilation, but prebuilt wheels are available for common platforms. Not necessary for general ML work outside the TOSA ecosystem.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; building from source requires a working C/C++ toolchain and CMake 3.18+.
- MLIR translator component requires a compatible LLVM/MLIR build.
- Medium install friction due to compiled native components requiring a C/C++ toolchain.
License · maintenance · safety
Apache-2.0 (permissive) — Licensed under Apache-2.0 (permissive), allowing broad commercial and private use with minimal restrictions beyond attribution and liability disclaimers.
last release 2026-05-21 (85 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 133,525 downloads/mo, #11,510 on PyPI
Alternatives
Verify before relying
python -m pip install tosa-tools
import tosa.serialization as tosa_ser
# Load a TOSA flatbuffer file
graph = tosa_ser.TosaGraph()
# Use graph for serialization or reference model operations- Whether prebuilt wheels cover all target platforms or if source compilation is often needed in practice
- Performance characteristics and scalability limits for large TOSA graphs
- Maturity and stability of experimental platform support (Windows, macOS, aarch64)
What it is and what it does
TOSA Tools is a composite toolkit implementing the Tensor Operator Set Architecture specification from Arm. It bundles three main components: a reference implementation of TOSA operators, serialization methods for reading and writing TOSA graphs in flatbuffer format, and an optional MLIR translator that converts between TOSA's MLIR dialect and serialized representations. The package is published on PyPI and installs as prebuilt wheels for supported platforms, or can be built from source with a C/C++ toolchain.
The toolkit is designed for developers working with TOSA-based machine learning workflows—particularly those integrating TOSA into compiler toolchains, validating operator implementations, or translating between different IR representations. It depends on numpy, flatbuffers, jsonschema, ml-dtypes, and semver for core functionality, and optionally integrates with LLVM/MLIR for translation tasks.
Use it for
- Serialize and deserialize TOSA operator graphs for interchange between ML frameworks and compiler backends
- Validate TOSA operator implementations using the reference model against specification compliance
- Translate TOSA MLIR dialect representations to and from flatbuffer serialized forms in compiler pipelines
- Integrate TOSA support into custom ML compiler toolchains requiring standardized operator semantics
- Test and debug TOSA graph transformations and optimizations before deployment
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are working with TOSA in a compiler, ML framework, or operator validation context.
The package is actively maintained, permissively licensed, supports current Python versions, and has no known vulnerabilities. Install friction is moderate due to native compilation, but prebuilt wheels are available for common platforms. Not necessary for general ML work outside the TOSA ecosystem.
Install
tosa-tools on PyPI
Before you install
Medium install friction due to compiled native components requiring a C/C++ toolchain. Package is actively maintained with recent releases and supports Python 3.10–3.13 across Linux (x86_64, aarch64), Windows, and macOS platforms, though some platforms are experimental.
Requires Python 3.10 or later; building from source requires a working C/C++ toolchain and CMake 3.18+. MLIR translator component requires a compatible LLVM/MLIR build.
License in practice
Licensed under Apache-2.0 (permissive), allowing broad commercial and private use with minimal restrictions beyond attribution and liability disclaimers.
Quickstart
python -m pip install tosa-tools
import tosa.serialization as tosa_ser
# Load a TOSA flatbuffer file
graph = tosa_ser.TosaGraph()
# Use graph for serialization or reference model operationsVerify before relying
- Whether prebuilt wheels cover all target platforms or if source compilation is often needed in practice
- Performance characteristics and scalability limits for large TOSA graphs
- Maturity and stability of experimental platform support (Windows, macOS, aarch64)
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 5 packagesnumpyflatbuffersjsonschemaml-dtypessemver |
| Maintenance | Actively maintained 85 days since the last release |
| First released | |
| Downloads | 133,525 / month, #11,510 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13 |
Evidence: tosa_tools-2026.5.0-cp310-cp310-macosx_15_0_arm64.whl; tosa_tools-2026.5.0-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; tosa_tools-2026.5.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; tosa_tools-2026.5.0-cp310-cp310-win_amd64.whl; tosa_tools-2026.5.0-cp311-cp311-macosx_15_0_arm64.whl; tosa_tools-2026.5.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; tosa_tools-2026.5.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; tosa_tools-2026.5.0-cp311-cp311-win_amd64.whl; tosa_tools-2026.5.0-cp312-cp312-macosx_15_0_arm64.whl; tosa_tools-2026.5.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; tosa_tools-2026.5.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; tosa_tools-2026.5.0-cp312-cp312-win_amd64.whl; tosa_tools-2026.5.0-cp313-cp313-macosx_15_0_arm64.whl; tosa_tools-2026.5.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; tosa_tools-2026.5.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; tosa_tools-2026.5.0-cp313-cp313-win_amd64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “TOSA serialization library”
- tosa-toolsTOSA Tools provides serialization, reference implementation, and…
- tosa-adapter-model-explorerEnables visualization of TOSA neural network model files within the…
- pyserdeSerialize and deserialize Python dataclasses to and from JSON, YAML,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also tosa-adapter-model-explorer · flatbuffers · xdsl · ai-edge-model-explorer · nvidia-nat-atif · flydsl · onnx2tf · nvidia-nat-eval · oslo.serialization