burn/crates/burn-ndarray
Guillaume Lagrange 3afff434bd
Module weight quantization (#2000)
* Add q_into_data and q_reshape

* Fix tch quantize f16 and q_into_data

* Convert to actual dtype/kind in dequantize

* Add module quantization and q_from_data

* Fix clippy

* Add documentation

* Handle deserialize data conversion

* Fix typo

* Add calibration tests

* Fix clippy precision

* Add QTensorOps require_grad methods to avoid dequantizing

* Add Dequantize mapper docs

* Remove dead code
2024-07-15 08:20:37 -04:00
..
src Module weight quantization (#2000) 2024-07-15 08:20:37 -04:00
Cargo.toml Add static tensor quantization (#1963) 2024-07-08 10:16:58 -04:00
LICENSE-APACHE Update licenses symlinks (#1613) 2024-04-12 14:43:58 -04:00
LICENSE-MIT Update licenses symlinks (#1613) 2024-04-12 14:43:58 -04:00
README.md [refactor] Move burn crates to their own crates directory (#1336) 2024-02-20 13:57:55 -05:00
build.rs [refactor] Move burn crates to their own crates directory (#1336) 2024-02-20 13:57:55 -05:00

README.md

Burn NdArray

Burn ndarray backend

Current Crates.io Version license

Feature Flags

This crate can be used without the standard library (#![no_std]) with alloc by disabling the default std feature.

The following flags support various BLAS options:

  • blas-accelerate - Accelerate framework (macOS only)
  • blas-netlib - Netlib
  • blas-openblas - OpenBLAS static linked
  • blas-openblas-system - OpenBLAS from the system

Note: under the no_std mode, the seed is fixed if the seed is not initialized by by Backend::seed method.

Platform Support

Option CPU GPU Linux MacOS Windows Android iOS WASM
Pure Rust Yes No Yes Yes Yes Yes Yes Yes
Accelerate Yes No No Yes No No Yes No
Netlib Yes No Yes Yes Yes No No No
Openblas Yes No Yes Yes Yes Yes Yes No