Skip to main content

Python bindings for the Ampere® optimized llama.cpp library

Project description

Python Bindings for Ampere® optimized llama.cpp

Simple Python bindings for Ampere® optimized llama.cpp based on @ggerganov's llama.cpp library and @abetlen's llama-cpp-python bindings This package maintains compatibility with the original project.

For best results we recommend using models in our custom quantization formats available here: AmpereComputing HF

This package can be run on bare metal Ampere® CPUs and Ampere® based VMs available in the cloud.

Support

Please contact us at ai-support@amperecomputing.com

License

By accessing, downloading or using this software and any required dependent software (the “Ampere AI Software”), you agree to the terms and conditions of the software license agreements for the Ampere AI Software, which may also include notices, disclaimers, or license terms for third party software included with the Ampere AI Software. Please refer to the LICENSE.md file.

Project details


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.

llama_cpp_python_ampere-0.3.16-cp313-cp313-manylinux_2_34_aarch64.whl (1.8 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.34+ ARM64

llama_cpp_python_ampere-0.3.16-cp312-cp312-manylinux_2_34_aarch64.whl (1.8 MB view details)

Uploaded CPython 3.12manylinux: glibc 2.34+ ARM64

llama_cpp_python_ampere-0.3.16-cp311-cp311-manylinux_2_34_aarch64.whl (1.8 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.34+ ARM64

llama_cpp_python_ampere-0.3.16-cp310-cp310-manylinux_2_34_aarch64.whl (1.8 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.34+ ARM64

File details

Details for the file llama_cpp_python_ampere-0.3.16-cp313-cp313-manylinux_2_34_aarch64.whl.

File metadata

File hashes

Hashes for llama_cpp_python_ampere-0.3.16-cp313-cp313-manylinux_2_34_aarch64.whl
Algorithm Hash digest
SHA256 99fcd4a6b4f5e6698f1810209a50fa7cfded7412e8ac193be823fae780cc4482
MD5 d183e333df618eef87187bc4c4f9f9f0
BLAKE2b-256 365215e07c7e027bc41ab3f20e55c925472789657b26cb9aaabb0e3f19ac9609

See more details on using hashes here.

File details

Details for the file llama_cpp_python_ampere-0.3.16-cp312-cp312-manylinux_2_34_aarch64.whl.

File metadata

File hashes

Hashes for llama_cpp_python_ampere-0.3.16-cp312-cp312-manylinux_2_34_aarch64.whl
Algorithm Hash digest
SHA256 6517c40086f7cf2f7c4e533565dd9f273f8b4e010d59fbc36818f1f06368c72d
MD5 e7ab3ff9310ed8927d26b73aa1dc4ba6
BLAKE2b-256 a30177500b14e674f8be12234e62d6875201b1e18592bce4f359b87ce277a6ba

See more details on using hashes here.

File details

Details for the file llama_cpp_python_ampere-0.3.16-cp311-cp311-manylinux_2_34_aarch64.whl.

File metadata

File hashes

Hashes for llama_cpp_python_ampere-0.3.16-cp311-cp311-manylinux_2_34_aarch64.whl
Algorithm Hash digest
SHA256 ed2fe0156b0778d8854ac7014ad405a4458e829aac7372a1bc08dbeed8655588
MD5 d7d581990331b5a22f71ab14421ff67a
BLAKE2b-256 7b1a19e2a4fe7c2046bff263e3d2864c8555bb2ae48813dd181d2303f619ef9c

See more details on using hashes here.

File details

Details for the file llama_cpp_python_ampere-0.3.16-cp310-cp310-manylinux_2_34_aarch64.whl.

File metadata

File hashes

Hashes for llama_cpp_python_ampere-0.3.16-cp310-cp310-manylinux_2_34_aarch64.whl
Algorithm Hash digest
SHA256 b2a9f6459eb10b4ab86beec5274577929dafcd0b7249962342241be46b6b31e7
MD5 b4cf06a9c7f164753c10e338688b55b3
BLAKE2b-256 f92b25b883186d3cac2f2b07c9ea75c579c76e9852466b0de0a38b5714b47f38

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page