#deep-learning #machine-learning #data

no-std burn-compute

Compute crate that helps creating high performance async backends

8 unstable releases (3 breaking)

0.13.2 May 3, 2024
0.13.1 Apr 26, 2024
0.12.1 Feb 1, 2024
0.12.0 Jan 31, 2024
0.10.0 Oct 24, 2023

#41 in #deep-learning

Download history 1257/week @ 2024-01-29 1112/week @ 2024-02-05 1122/week @ 2024-02-12 1090/week @ 2024-02-19 1075/week @ 2024-02-26 1155/week @ 2024-03-04 1139/week @ 2024-03-11 2007/week @ 2024-03-18 4510/week @ 2024-03-25 3912/week @ 2024-04-01 2056/week @ 2024-04-08 3848/week @ 2024-04-15 2878/week @ 2024-04-22 3610/week @ 2024-04-29 2143/week @ 2024-05-06 1911/week @ 2024-05-13

10,920 downloads per month
Used in 11 crates (2 directly)

MIT/Apache

86KB
2K SLoC

Burn Compute

This crate helps creating high performance async backends.

  • Asynchronous kernel executions
  • Memory allocation management
  • Autotuning

lib.rs:

Burn compute crate that helps creating high performance async backends.

Dependencies

~3–13MB
~121K SLoC