candle

candle copied to clipboard

Problem loading metadata of gguf file

6

I encountered an error while executing the example [quantized-phi](https://github.com/huggingface/candle/tree/main/candle-examples/examples/quantized-phi), which I slightly modified. However, I suspect the issue might not be with my modifications. The problem seems to be related...

cnlancehu

Refactor the metal backend to always reuse command encoders/buffers unless a shared memory access is requested

9

This change aims to replace the pattern of each tensor provisioning a command buffer and encoder for each kernel operation that occurs, to a pattern where an encoder is provided...

tomsanbear

Quantized Phi-3 example fails "cannot find llama.attention.head_count in metadata"

4

``` cargo run --example quantized-phi --release -- --prompt "what is the best thing about rust?" --which phi-3 Compiling candle-examples v0.5.0 (/Users/kenk/Documents/Code/OpenSource/candle/candle-examples) Finished release [optimized] target(s) in 3.21s Running `target/release/examples/quantized-phi --prompt...

MoonKraken

`broadcast_as` error when processing multiple tokens at once in quantized example

9

Hello all, Thanks for your great work here. We are implementing speculative decoding at mistral.rs, and were in the final stages of testing when we discovered some incredibly strange behavior....

EricLBuehler

linking with `link.exe` failed: exit code: 1120

5

i try to compile candle in windows. ```bash cargo run --example stable-diffusion --release --features=cuda,cudnn -- --prompt "a cosmonaut on a horse (hd, realistic, high-def)" ``` it failed on link ```bash...

kulame

Transparent Huge Pages Support

2

When working with CPU tensors on Linux, transparent huge pages (THP) can provide a big speedup. For example, I see a 15% increase in speed for my code when I...

michaeleisel

A common operation for me is filtering down a tensor to a subset of it based on some condition. For example, I may want to filter out all the rows...

michaeleisel

AudioGen/MusicGen

7

Are there any plans to implement the AudioGen/MusicGen models from Facebook?

KookaburraShell

This PR implements forward method for musicgen model: huggingface/candle#975

qooba

Low time effiency when run cnn on mnist-traning only with CPU

3

I try to use the following command to train the CNN model with mnist-training example. It works well when training linear and mlp model, but when I config it to...

Viewer-HX