huggingface candle issues

huggingface / candle

Minimalist ML framework for Rust

Apache License 2.0

15.88k stars 962 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Set element in an Tensor

#2635 DimitriTimoz opened 19 hours ago
0
Windows Cuda Compatibility?

#2633 ChaseLewis opened 3 days ago
0
Cannot download CIFAR-10

#2632 VillSnow opened 3 days ago
1
CUDA Version: 12.6 Falcon Example Out Of Memory Error

#2631 gx14ac closed 3 days ago
2
Tweak the CI to avoid running out of disk space.

#2630 LaurentMazare closed 3 days ago
0
20241118 docs

#2629 zachcp closed 3 days ago
1
Import the ggml_cuda_dp4a function.

#2628 LaurentMazare closed 3 days ago
0
SM80 support means only expensive GPUs can be used. Can SM60 and above be supported?

#2627 profitgrowinginnovator opened 4 days ago
3
Fix for clippy.

#2626 LaurentMazare closed 4 days ago
0
Fix example build for bigcode

#2625 synapse-overload closed 4 days ago
2
Module Docs

#2624 zachcp closed 4 days ago
0
More Model Module Docs

#2623 zachcp closed 4 days ago
11
How to compute `Atan2` for tensors?

#2622 cryscan opened 6 days ago
1
candle-transformers is not compiling

#2621 profitgrowinginnovator closed 4 days ago
2
Module Docs

#2620 zachcp closed 6 days ago
0
Debug formatter for `Tensor` is confusing with > 1 GPU

#2619 zackangelo opened 1 week ago
1
Remove some unused macros.

#2618 LaurentMazare closed 1 week ago
0
Documentation Pass for Models

#2617 zachcp closed 1 week ago
1
Add max-all/min-all.

#2616 LaurentMazare closed 1 week ago
0
*Major T/s improvement* Use the Metal qmatmul MM kernels

#2615 EricLBuehler opened 1 week ago
1
Feat Request: `Candle-Info`

#2614 zachcp opened 1 week ago
0
Add some missing index-select metal kernels.

#2613 LaurentMazare closed 1 week ago
0
Bump the crate version to 0.8.0.

#2612 LaurentMazare closed 1 week ago
0
Error encountered when running the example Chinese clip with Metal

#2611 BB-fat closed 1 week ago
2
Compilation errors due to incorrect GPU architecture

#2610 profitgrowinginnovator opened 1 week ago
0
Model support: wav2vec2

#2609 harryfei opened 1 week ago
0
Adds support for stella_en_v5 embedding model -400M variant

#2608 iskng opened 1 week ago
4
[chore] Fix small typo in doc string of `Tensor::zeros_like`

#2606 nerdai opened 2 weeks ago
0
Mirror "Arm AArch64: optimized GEMV and GEMM kernels for q4_0_q8_0, and q8_0_q8_0 quantization" from llama.cpp

#2605 smpurkis opened 2 weeks ago
0
WebNN support

#2604 allsey87 opened 2 weeks ago
3
Add LRSchedulers

#2603 DimitriTimoz opened 2 weeks ago
0
Masked fill: slow operations compared to tch for small models

#2602 JHucker opened 2 weeks ago
0
Implement BertPooling

#2601 DimitriTimoz opened 2 weeks ago
0
Use nn.Dropout for BertModel

#2600 DimitriTimoz closed 2 weeks ago
0
rand problem on GPU

#2599 LonlyWinter closed 2 weeks ago
2
Cannot compile candle-transformers

#2598 sneilan closed 2 weeks ago
2
Stable Diffusion 3.5 Large CUDA OUT_OF_MEMORY on RTX 3090

#2597 danielclough opened 2 weeks ago
10
Sdpa stride fix

#2596 EricLBuehler closed 2 weeks ago
0
Add the SmolLM2 models.

#2595 LaurentMazare closed 2 weeks ago
0
Add Huggingface SmolLM models

#2594 akashicMarga closed 2 weeks ago
1
Model support: OmniGen

#2593 Czxck001 opened 2 weeks ago
1
Einops-like API

#2592 someone13574 closed 2 weeks ago
1
Improved launch config for layer-norm/rms-norm.

#2591 LaurentMazare closed 2 weeks ago
0
Support Skip Layer Guidance (SLG) for Stable Diffusion 3.5 Medium

#2590 Czxck001 closed 3 weeks ago
1
Lazy upcasting for t5.

#2589 LaurentMazare closed 3 weeks ago
1
Support Skip Layer Guidance (SLG) for Stable Diffusion 3.5 Medium

#2588 Czxck001 closed 3 weeks ago
1
Support sd3.5 medium and MMDiT-X

#2587 Czxck001 closed 3 weeks ago
1
Shape mismatch in where_cond

#2586 jiabochao closed 2 weeks ago
0
Where are models saved?

#2585 IgChar opened 3 weeks ago
2
Add some fast Metal MLX SDPA kernels

#2584 EricLBuehler closed 2 weeks ago
2