mirror of
https://github.com/huggingface/candle.git
synced 2025-06-16 10:38:54 +00:00

* Added dequantization for `q4_0`, `q4_1`, `q5_0`, `q5_1` and `q8_0` * expose `tensor_from_ggml` for external usage * bugfixes & example
* Added dequantization for `q4_0`, `q4_1`, `q5_0`, `q5_1` and `q8_0` * expose `tensor_from_ggml` for external usage * bugfixes & example