Skip to content

Pull requests: huggingface/candle

New pull request New
148 Open 2,105 Closed
148 Open 2,105 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Upgrade GitHub Actions for Node 24 compatibility
#3255 opened Dec 20, 2025 by salmanmkc Loading…
Optimization for CPU Causal Flash Attention (integrated into Qwen3)
#3254 opened Dec 20, 2025 by DrJesseGlass Loading…
add HuberLoss and add Loss Trait
#3252 opened Dec 20, 2025 by donjuanplatinum Loading…
add the momentum and Nesterov(NAG) support for SGD optimizer like pytorch
#3251 opened Dec 20, 2025 by donjuanplatinum Loading…
feat: implementation varlen-flash-attention on cpu
#3250 opened Dec 18, 2025 by michaelfeil Loading…
3
Add Mistral3 vision-language model support (For Flux2 Migration)
#3246 opened Dec 16, 2025 by SpenserCai Loading…
5 tasks done
feat: allow tokenizer to load from GGUF metadata
#3245 opened Dec 16, 2025 by fffonion Loading…
feat: add quantized lfm2 model support
#3244 opened Dec 16, 2025 by fffonion Loading…
feat: Swin Transformer v1 Support
#3243 opened Dec 15, 2025 by danielclough Loading…
Add bilinear interpolation support (upsample_bilinear2d)
#3237 opened Dec 9, 2025 by SpenserCai Loading…
4
feat(qwen2): add KV cache management and selective attention
#3236 opened Dec 9, 2025 by danielclough Loading…
replace cutlass submodule references with explicit build step
#3234 opened Dec 8, 2025 by jacobgorm Loading…
add quantized qwen3 moe module
#3232 opened Dec 8, 2025 by TheoLee72 Loading…
fix: inplace-op2 shared storage deadlock
#3229 opened Dec 6, 2025 by junjunjd • Draft
1
Fix cudarc deprecation warnings for memcpy methods
#3228 opened Dec 5, 2025 by DrJesseGlass Loading…
make candle ops public
#3226 opened Dec 4, 2025 by zackangelo • Draft
Add yolo-v5 example
#3224 opened Dec 3, 2025 by mayocream Loading…
1
8
Support Fused MoE & Qwen3 GGUF MoE models
#3221 opened Dec 2, 2025 by guoqingbao Loading…
6
fix: add gguf wrapper in quantized gemma3
#3220 opened Dec 2, 2025 by junjunjd Loading…
1
Add Rust Metrics to list of external resources
#3217 opened Nov 27, 2025 by shaankhosla Loading…
Pinned memory
#3216 opened Nov 27, 2025 by ahadnagy Loading…
7
[WIP] TensorResult abstraction
#3214 opened Nov 25, 2025 by ivarflakstad • Draft
2
feat: Add BertForTokenClassification for Named Entity Recognition in Rust
#3212 opened Nov 24, 2025 by MSkill1 Loading…
Metal: bound temporary buffer cache and prevent runaway memory usage on large softmax/broadcast/matmul workloads
#3197 opened Nov 17, 2025 by TimmyOVO Loading…
32
Add Provence model implementation
#3191 opened Nov 17, 2025 by matthewhaynesonline • Draft
1
ProTip! What’s not been updated in a month: updated:<2025-11-21.