Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

Windows ML llama.cpp backend for Python

These distributions add the optional llama.cpp backend to the windowsml Python package. With the core installed, the Windows ML Runtime loads GGUF models on the CPU.

pip install windowsml-llama-core

The core carries the llama.cpp adapter, the llama.cpp and ggml modules, and the CPU backend. It pins the exact windowsml version it was built with and installs its payload into windowsml/lib, beside that Runtime.

GPU backends are optional, installed separately, and must be compatible with this Runtime. Their third-party dependencies have their own license terms.

Metadata

Release files for windowsml-llama-core 2.9.36a0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for windowsml-llama-core 2.9.36a0
File Interpreter ABI Platform Actions
windowsml_llama_core-2.9.36a0-py3-none-win_arm64.whl Python 3 none Windows ARM64 Details for windowsml_llama_core-2.9.36a0-py3-none-win_arm64.whl
windowsml_llama_core-2.9.36a0-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details for windowsml_llama_core-2.9.36a0-py3-none-win_amd64.whl

Total release size: 7.3 MB

Release files / windowsml_llama_core-2.9.36a0-py3-none-win_arm64.whl

Download URL windowsml_llama_core-2.9.36a0-py3-none-win_arm64.whl
Size 3.6 MB
Tags Python 3 Windows ARM64
SHA-256 checksum
How to use checksums
fdc3470d1d740fc981b5a1b34cf29f5293a5124553d16364015cc215c57bc5dd
BLAKE2b-256 checksum
How to use checksums
45df9529d860cecaf603e82f29a0ffc912d2b6abf7c4b904d0b225713aa9cae2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via RestSharp/106.13.0.0

Release files / windowsml_llama_core-2.9.36a0-py3-none-win_amd64.whl

Download URL windowsml_llama_core-2.9.36a0-py3-none-win_amd64.whl
Size 3.6 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
d76490b4f1cfb047c6319954ee79261043cc1772355067821101090040adfa57
BLAKE2b-256 checksum
How to use checksums
102c75635de03b558886bb472a1c7ad47cac75de55a1ddb65d2849cda4379f16
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via RestSharp/106.13.0.0

Security for windowsml-llama-core 2.9.36a0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page