Skip to main content

GPU Memory & Math Library

Project description

ADAMAH

GPU Memory & Math Library - As simple as possible, but complete.

import adamah

adamah.init()
adamah.put("x", [0, 1, 2, 3])
adamah.sin("y", "x", 4)
print(adamah.get("y"))  # [0, 0.841, 0.909, 0.141]
adamah.shutdown()

Install

pip install adamah

Requires: libvulkan-dev (auto-compiles on first use)

Usage

import adamah

# Context manager (recommended)
with adamah.Adamah() as gpu:
    gpu.put("a", [1, 2, 3, 4])
    gpu.put("b", [4, 3, 2, 1])
    gpu.add("c", "a", "b", 4)
    print(gpu.get("c"))  # [5, 5, 5, 5]

# Or functional API
adamah.init()
adamah.put("x", data)
adamah.sin("y", "x", len(data))
result = adamah.get("y")
adamah.shutdown()

Operations

  • Math: sin, cos, tan, exp, log, sqrt, tanh, relu, gelu
  • Ops: add, sub, mul, div, pow
  • Reduce: sum, max, min, mean, prod
  • Calculus: cumsum, diff, integrate, derivative
  • Linear Algebra: dot, matvec, softmax
  • Generators: linspace, arange
  • Sparse: scatter/gather memory maps

License

CC BY-NC 4.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

adamah-3.0.0.tar.gz (10.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

adamah-3.0.0-py3-none-any.whl (11.3 kB view details)

Uploaded Python 3

File details

Details for the file adamah-3.0.0.tar.gz.

File metadata

  • Download URL: adamah-3.0.0.tar.gz
  • Upload date:
  • Size: 10.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for adamah-3.0.0.tar.gz
Algorithm Hash digest
SHA256 5a18f478d4e422dc0501f64dff3d21fc036559d078160623c00bbdb9c28a7a2a
MD5 b5bbb94116a45259d2c4410d675da9f6
BLAKE2b-256 cb69d55c451d3a9814753a0fd52ffef32b4b97a4c0f8ac8de0e5d25dd064a808

See more details on using hashes here.

File details

Details for the file adamah-3.0.0-py3-none-any.whl.

File metadata

  • Download URL: adamah-3.0.0-py3-none-any.whl
  • Upload date:
  • Size: 11.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for adamah-3.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6ea4d2b8a1fc458950fd99fa654e28c40646982e79a47ebe7625fc0143c0bf5e
MD5 f8a34af57dc1b8cdbaafc9fb4de6317c
BLAKE2b-256 15c66f3d66b7a7aeee8d8c86ce062303f16a1450478f014b7e1c59a9c4ee1c70

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