candle
candle copied to clipboard
huggingface
Minimalist ML framework for Rust
I want to make a simple multi class classification using resnet50 model but receiving errors. I am receiving error on step ``adam.backward_step(&loss).unwrap()`` ```rust let num_classes = 2; let vm =...
I'm experimenting with the new implementation of CUDA acceleration for quantized models and wondering how to use sharded tensors in this context. I'm having a hard time adapting the `ShardedVarBuilder`...
I'm looking to leverage more of my GPU when running multiple models in parallel. It'd be great if candle had some sort of support for running multiple concurrent streams at...
I dived into the issues and repo about the subject, because I wanted to be able to call cuda kernels regarding 3D gaussian splatting, and the way to invoke those...
Adds a python pretty printer for GDB for Tensor values. Tensor values in GDB now have a "desc" field that contains a formatted view of the tensor similar to the...
I need to see tensor values and shape. Hardcoding println is inconvenient. This seems to be less convenient than python. I wonder if there is a better way.
Maybe CPU probing should detect whether AVX2 is available as a start. If it is determined that AVX should be supported perhaps let the probe set an enum to what...
It seems that tensor is dropped, and others are fine. When run this line code [candle-examples/examples/llama_multithread/model.rs#L177](https://github.com/mokeyish/candle/blob/llam_multithread/candle-examples/examples/llama_multithread/model.rs#L177) it throws an error as following: ```txt Cuda(Load { cuda: DriverError(CUDA_ERROR_ILLEGAL_ADDRESS, "an illegal memory...
Ran Phi 2 model with the metal features enabled and seems to hang with about 7% of GPU usage from Activity monitor. This seems to be recent as it ran...
