Skip to content

Pull requests: huggingface/candle

New pull request New
Clear current search query, filters, and sorts
99 Open 1,859 Closed
99 Open 1,859 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Gemma 3 initial setup (text only).
#2802 opened Mar 12, 2025 by LaurentMazare Loading… updated Mar 12, 2025
Add candle-nn::Sequential::new() constructor
#2801 opened Mar 10, 2025 by slckl Loading… updated Mar 10, 2025
Add Qwen2.5 Instruct model
#2797 opened Mar 8, 2025 by ITHwang Loading… updated Mar 8, 2025
Implement I-quants (IQ4XS, IQ4NL)
#2785 opened Feb 24, 2025 by EricLBuehler Loading… updated Mar 3, 2025
9
perf: Optimize to_dtype using specialized as_ methods
#2768 opened Feb 12, 2025 by haricot Loading… updated Feb 25, 2025
Fix bug for asort kernel & faster sampler with GPU sorting
#2730 opened Jan 21, 2025 by guoqingbao • Draft updated Feb 25, 2025
4
Implement DeepSeek V3/R1
#2745 opened Jan 27, 2025 by EricLBuehler Loading… updated Feb 24, 2025
3 tasks done
1
Fix candle-core example basics.rs
#2783 opened Feb 22, 2025 by chammika Loading… updated Feb 22, 2025
Add simple test for embedding function
#2777 opened Feb 21, 2025 by viirya Loading… updated Feb 21, 2025
WIP: MLLaMA-Vision Model Implementation with Candle
#2773 opened Feb 15, 2025 by elk-cloner • Draft updated Feb 19, 2025
6 tasks
3
Vectorized CPU implementation for various unary functions for f32
#2752 opened Jan 28, 2025 by mert-kurttutan Loading… updated Feb 14, 2025
11
Fix typo in tensor_cat.rs
#2765 opened Feb 9, 2025 by 0xNaN Loading… updated Feb 9, 2025
add cuda fallback bf16 for compute_cap >=530 <800
#2704 opened Jan 7, 2025 by haricot • Draft updated Feb 8, 2025
4
[AArch64] Quantized MatMul performance improvement
#2536 opened Oct 3, 2024 by bgergely0 Loading… updated Feb 4, 2025
1
ModernBertForTokenClassification
#2758 opened Jan 31, 2025 by scampion Loading… updated Jan 31, 2025
*Major T/s improvement* Use the Metal qmatmul MM kernels
#2615 opened Nov 14, 2024 by EricLBuehler Loading… updated Jan 29, 2025
2
Various improvements to low-rank + quantized backpropagation,
#2729 opened Jan 19, 2025 by computer-whisperer Loading… updated Jan 27, 2025
1
[Draft]: Add flash attention to whisper (unsure how correct this is)
#2722 opened Jan 16, 2025 by Murad-Awad • Draft updated Jan 16, 2025
1
Refactor/ops step1 : Introduce OpsRegistry to simplify operators development and enable incremental refactoring (#2638)
#2644 opened Nov 27, 2024 by imihalcea Loading… updated Jan 12, 2025
5
Add Support for mixed quantized BitNet Architecture Inference
#2683 opened Dec 27, 2024 by JoseCarlosGarcia95 Loading… updated Jan 1, 2025
1
Add Support for BitNet Architecture Inference
#2664 opened Dec 9, 2024 by JoseCarlosGarcia95 Loading… updated Dec 31, 2024
14
fix basics example
#2679 opened Dec 24, 2024 by majian4work Loading… updated Dec 24, 2024
Dep Version Bump
#2663 opened Dec 8, 2024 by zachcp • Draft updated Dec 8, 2024
Custom backend support
#1466 opened Dec 22, 2023 by agerasev Loading… updated Dec 4, 2024
3
Musicgen forward implementation
#2145 opened Apr 30, 2024 by qooba Loading… updated Dec 1, 2024
1
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.