candle
candle copied to clipboard
huggingface
Minimalist ML framework for Rust
I got error CUDA_ERROR_INVALID_VALUE when running the code on cuda device. But the same code is running fine in cpu device. ``` use candle_core::{Device, DType, Tensor}; fn main() -> Result...
~~Sorry to open a draft again~~, but while adding more models I found out why the DinoV2 example loads its safetensors from a different location than Facebook's own HF space:...
I was wanting to test quantization for CLIP for use in WASM and wrote this for my own but wanted to upstream it. For making the quantized version, I have...
Updates the requirements on [gemm](https://github.com/sarah-ek/gemm) to permit the latest version. Commits a3d481f Release 0.17.1 See full diff in compare view You can trigger a rebase of this PR by commenting...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
https://pytorch.org/docs/stable/generated/torch.multinomial.html. If it is not implemented, I can implement this interface
pow implemented as f32/f64 ln and exp works only for positive base. Then intent of this change is to support negative bases as well, and to that end, the current...
Hello everybody, Is there away to freeze all Var Tensors in the VarMap like the below snippet ? means something like implement the `Iterator` trait and detach the contained tensors...
currently the cpu backend incorrectly converts negative i64 to usize by casting, but it should check if the index is negative, and in that case, count back from the end...
cat /etc/issue Debian GNU/Linux 12 \n \l rustc -V rustc 1.77.0-nightly (d5fd09972 2024-01-22) gcc -v Using built-in specs. COLLECT_GCC=gcc COLLECT_LTO_WRAPPER=/usr/lib/gcc/aarch64-linux-gnu/12/lto-wrapper Target: aarch64-linux-gnu Configured with: ../src/configure -v --with-pkgversion='Debian 12.2.0-14' --with-bugurl=file:///usr/share/doc/gcc-12/README.Bugs --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2...
