Skip to content

Issues: huggingface/candle

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

326 Open 383 Closed
326 Open 383 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Compilation errors due to incorrect GPU architecture
#2610 opened Nov 11, 2024 by profitgrowinginnovator
Model support: wav2vec2
#2609 opened Nov 11, 2024 by harryfei
Mirror "Arm AArch64: optimized GEMV and GEMM kernels for q4_0_q8_0, and q8_0_q8_0 quantization" from llama.cpp
#2605 opened Nov 8, 2024 by smpurkis
WebNN support
#2604 opened Nov 8, 2024 by allsey87
Masked fill: slow operations compared to tch for small models
#2602 opened Nov 7, 2024 by JHucker
Stable Diffusion 3.5 Large CUDA OUT_OF_MEMORY on RTX 3090
#2597 opened Nov 5, 2024 by danielclough
3
Model support: OmniGen
#2593 opened Nov 3, 2024 by Czxck001
1
Where are models saved?
#2585 opened Oct 29, 2024 by IgChar
2
Support for Stable Diffusion 3.5 Large
#2574 opened Oct 25, 2024 by super-fun-surf
7
Add support for the quantized llama 3.2 models
#2573 opened Oct 25, 2024 by a-agmon
Running mamba seems to run single threaded on NixOs with AMD CPU
#2571 opened Oct 20, 2024 by Corallus-Caninus
2
[BUG] argsort metal kernel yields incorrect output with > 1024 elements
#2570 opened Oct 20, 2024 by AnubhabB
2
Add support for Nvidia Llama3.1-Nemotron 70B instruct
#2566 opened Oct 16, 2024 by jorgeantonio21
book-cd.yml uses a deprecated Node.js version
#2564 opened Oct 15, 2024 by hamirmahal
1
1
binary_cross_entropy_with_logit numerically unstable for high logits
#2561 opened Oct 14, 2024 by BeneSim
Pytorch Lightning-Like Api
#2549 opened Oct 7, 2024 by someone13574
1
MaziyarPanahi/gemma-2b-it-GGUF
#2540 opened Oct 4, 2024 by ktmobility1
mlx-community/gemma-2-2b-it-4bit infer error
#2537 opened Oct 3, 2024 by ktmobility1
1
Unable to use any CLIP model with model_id
#2520 opened Sep 29, 2024 by akshayballal95
Quantized Flux not working
#2511 opened Sep 28, 2024 by donkey-donkey
9
Does Candle support Arm Kleidi in the future?
#2506 opened Sep 26, 2024 by kigichang
Incompatible shapes when
#2501 opened Sep 25, 2024 by segeljakt
1
broadcast_add is very slow
#2499 opened Sep 25, 2024 by okpatil4u
2
CUDA_ERROR_UNSUPPORTED_PTX_VERSION when loading is_u32_f32
#2498 opened Sep 24, 2024 by super-fun-surf
2
ONNX MaxPool auto_pad missing options
#2497 opened Sep 24, 2024 by vesuvisian
ProTip! Type g i on any issue or pull request to go back to the issue listing page.