#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

#906 in Machine learning

Download history 2675/week @ 2024-04-03 2617/week @ 2024-04-10 3371/week @ 2024-04-17 3564/week @ 2024-04-24 2954/week @ 2024-05-01 2061/week @ 2024-05-08 2162/week @ 2024-05-15 3618/week @ 2024-05-22 2835/week @ 2024-05-29 4530/week @ 2024-06-05 3189/week @ 2024-06-12 1855/week @ 2024-06-19 2392/week @ 2024-06-26 2442/week @ 2024-07-03 1582/week @ 2024-07-10 1322/week @ 2024-07-17

7,996 downloads per month
Used in 14 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

~3–14MB
~123K SLoC