candle
candle copied to clipboard
huggingface
Minimalist ML framework for Rust
## Summary Adds `ignore_index` support to cross-entropy and NLL loss functions via new `*_with_ignore` functions, enabling proper handling of padding tokens in sequence modeling. ## Motivation Sequence modeling (NLP, time...
Hello, author. Do you have any plans to support model fine-tuning
tested and works with: ``` nvidia-smi --query-gpu="compute_cap" --format=csv compute_cap 6.1 ``` ``` cargo run -F "cuda,cudnn" --example llama --release -- --model-id meta-llama/Llama-3.2-1B-Instruct --temperature 0.1 --which v32-1b-instruct --seed 42 --dtype bf16...
Hi team! Thanks to the awesome work that bringing rust to the game! I found that the usage of `LogitsProcessor` in the quantized example is not proper which makes the...
This PR adds a new github workflow that aims to improve the release workflow. The workflow requires manually triggering and checks that the intended release semver version matches the version...
When I run `cargo run --example stable-diffusion-3 --release --features=cuda -- --which 3.5-large --prompt "pretty picture"` I am get `Error: DriverError(CUDA_ERROR_OUT_OF_MEMORY, "out of memory")` with Stable Diffusion 3.5 Large and Turbo....
Several vision-language models such as Qwen-VL and its variants make use of 3D convolution layers (Conv3D) in their architecture, especially for handling video or temporal spatial data. Currently, Candle does...
This PR introduces a unified and extensible interface and serialization format. Key updates: Adds ConcurrentVarMap (RwLock-based) for high-performance, concurrent inference. Refactors VarMap to use a generic storage backend, preserving the...
