diff options
| author | Laurent Mazare <laurent.mazare@gmail.com> | 2023-08-15 22:45:53 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-08-15 22:45:53 +0100 |
| commit | ca449f9ee11b892e026972d114c77a0938e1dc0b (patch) | |
| tree | fd179ab9ffd5d1a3da740506a091147df9ba39e5 /candle-examples/examples/ggml/main.rs | |
| parent | b8263aa15cf2d8d0f425e25bae296ea4e96aeb88 (diff) | |
| download | candle-ca449f9ee11b892e026972d114c77a0938e1dc0b.tar.gz candle-ca449f9ee11b892e026972d114c77a0938e1dc0b.tar.bz2 candle-ca449f9ee11b892e026972d114c77a0938e1dc0b.zip | |
Add quantized tensors. (#458)
* Add quantized tensors.
* Implement the debug trait for QTensor.
* Add the QMatMul custom op.
Diffstat (limited to 'candle-examples/examples/ggml/main.rs')
| -rw-r--r-- | candle-examples/examples/ggml/main.rs | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/candle-examples/examples/ggml/main.rs b/candle-examples/examples/ggml/main.rs index 78eb20dc..9e3e1ba6 100644 --- a/candle-examples/examples/ggml/main.rs +++ b/candle-examples/examples/ggml/main.rs @@ -3,7 +3,6 @@ use clap::Parser; use std::fs::File; use candle::quantized::ggml_file::Content; -use candle::{DType, Device}; #[derive(Parser, Debug)] #[command(author, version, about, long_about = None)] @@ -18,7 +17,7 @@ fn main() -> Result<()> { let mut file = File::open(args.model)?; let start = std::time::Instant::now(); - let model = Content::read(&mut file, DType::F16, &Device::Cpu)?; + let model = Content::read(&mut file)?; println!( "Loaded {:?} tensors in {:?}", |