candle
candle copied to clipboard
huggingface
Minimalist ML framework for Rust
Currently not able to load diffusers models as is due to difference in layout, viz. for SDXL if I try to load [SDXL FaeTastic](https://civitai.com/models/129681?modelVersionId=291443) it will error out following the...
vLLM v1 uses CUDA Graph to capture the execution workflow of the entire model, resulting in significant performance improvements compared to the previous version. I'm wondering if there are any...
HI, since many TTS model based on a Qwen0.5B model + SNAC, would consider support SNAC? so that users can easily deploy their TTS model in pure Rust.
Is anyone already working on implementing the OpenAI open-source models? If so, I can help out. There are some blockers right now: - [ ] Support for MXFP4 checkpoints. See...
## Overview This draft PR proposes adding a new `candle-utils` crate that provides higher-level abstractions for common patterns found throughout the Candle examples. The goal is to reduce boilerplate for...
## Motivation Candle's WASM build currently runs on a single CPU thread, which makes it significantly slower than it could be. This PR provides a working demo of multithreaded WASM...
Tried running the `candle-core` test suite on a 5070 and got these errors: ``` failures: ---- argmin_gpu stdout ---- thread 'argmin_gpu' panicked at candle-core/tests/tensor_tests.rs:548:5: assertion `left == right` failed left:...
