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-cuda 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-cuda 2.9.36a0
File Interpreter ABI Platform Actions
windowsml_llama_cuda-2.9.36a0-py3-none-win_arm64.whl Python 3 none Windows ARM64 Details for windowsml_llama_cuda-2.9.36a0-py3-none-win_arm64.whl
windowsml_llama_cuda-2.9.36a0-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details for windowsml_llama_cuda-2.9.36a0-py3-none-win_amd64.whl

Total release size: 120.0 MB

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

Download URL windowsml_llama_cuda-2.9.36a0-py3-none-win_arm64.whl
Size 42.3 MB
Tags Python 3 Windows ARM64
SHA-256 checksum
How to use checksums
21f972daad7605c89740cde7a42aca437b49c5c5254366439102bd3a99a9f02d
BLAKE2b-256 checksum
How to use checksums
46ff9da0bfc1ec33ada8b73adb2c1d7bd1590d9ba8a82118919f78c3810c02dd
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via RestSharp/106.13.0.0

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

Download URL windowsml_llama_cuda-2.9.36a0-py3-none-win_amd64.whl
Size 77.7 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
5fc84d1b899ee3720af66116f49eee58051638b512b0372923725310bcde69e4
BLAKE2b-256 checksum
How to use checksums
432ad475911ac4befbcd4d38f05207dbc2d1092e1831a3ca4fe0b8e2b121ec99
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via RestSharp/106.13.0.0

Security for windowsml-llama-cuda 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.

Release history Release notifications | RSS feed

This release
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