huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-20 12:06:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Expose some helper functions to create quantized models. (#1837)

Browse Source
This commit is contained in:
Laurent Mazare
2024-03-12 11:30:24 +01:00
committed by GitHub
parent df5f69444e
commit ff03fd3fb3
3 changed files with 15 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
candle-transformers/src/models/with_tracing.rs
View File

@ -116,6 +116,12 @@ impl QMatMul {
let span = tracing::span!(tracing::Level::TRACE, "qmatmul");
Ok(Self { inner, span })
}
pub fn from_weights(ws: std::sync::Arc<candle::quantized::QTensor>) -> Result<Self> {
let inner = candle::quantized::QMatMul::from_arc(ws)?;
let span = tracing::span!(tracing::Level::TRACE, "qmatmul");
Ok(Self { inner, span })
}
}
impl Module for QMatMul {