mirror of
https://github.com/huggingface/candle.git
synced 2025-06-15 10:26:33 +00:00
403680f17d
* Metal quantized modifications proposal. - Add a device param, wherever needed. - Create new QMetal storage thing that implements QuantizedType. - Update everywhere needed. Fix Python. Fixing examples. Fix: fmt + clippy + stub. Moving everything around. Only missing the actual implems. Fixing everything + adding dequantized kernels. More work. Fixing matmul. Fmt + Clippy Some clippy fixes. Working state. Q2K Metal -> Bugged (also present in GGML). Q4K CPU -> Bugged (present previously, new test catch it). Q5K CPU -> Bugged (present previously). Q8_1 Both -> Never really implemented it seems Q8K metal -> Never implemented in metal Fixing Q2K bug (present in ggml). * Cleanup. * Fix the rebase. * Removing the fences speeds everything up and *is* correct this time... * Cleanup the fence. * After rebase. * Bad code removal. * Rebase after phi2 merge + fix replit default to CPU. * Making the CI happy. * More happy tests. --------- Co-authored-by: Nicolas Patry <nicolas@Nicolass-MacBook-Pro.local>
candle-blip
The blip-image-captioning model can generate captions for an input image.
Running on an example
cargo run --example blip --release -- --image candle-examples/examples/yolo-v8/assets/bike.jpg
Running on CPU, to run on GPU, build this example with `--features cuda`
loaded image Tensor[dims 3, 384, 384; f32]
model built
several cyclists are riding down a road with cars behind them%
