burn/crates/burn-fusion
Guillaume Lagrange 0d5025edbb
Refactor tensor quantization for q_* ops (#2025)
* Move QuantizationScheme to burn-tensor

* Refactor QuantizedTensorPrimitive to include the quantization strategy

* Fix QFloat tensor data display

* Refactor quantization methods to use scheme and qparams (on backend device)

* Fix clippy

* Fix fmt

* Add qtensor primitive tests
2024-07-19 10:39:50 -04:00
..
src Refactor tensor quantization for q_* ops (#2025) 2024-07-19 10:39:50 -04:00
Cargo.toml Fix `DataSerialize` conversion for elements of the same type (#1832) 2024-05-28 18:12:44 -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

README.md

Burn Fusion

A kernel fusion backend decorator for Burn.