kernels-community/kernel-status
Viewer • Updated • 1.48k • 2.12k • 1
kernels-community
Team
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Team members 4 private
kernels-bot
updated a
dataset about 1 hour ago
Fused Triton attention for DeBERTa-v2/v3 - Disentangled Flash
2
#31 opened about 2 months ago
by 
delyanboychev
Post
86
We released kernels 0.18 🚀:
https://github.com/huggingface/kernels/releases/tag/v0.18.0
This version add support for Google TPU, Torch 2.15, stronger backwards compatibility for older Torch versions, new command-line utilities, and kernel signature/digest verification.
https://github.com/huggingface/kernels/releases/tag/v0.18.0
This version add support for Google TPU, Torch 2.15, stronger backwards compatibility for older Torch versions, new command-line utilities, and kernel signature/digest verification.
sayakpaul
authored a
paper 2 months ago
sayakpaul
submitted a
paper to Daily Papers 2 months ago
sayakpaul
authored 4
papers 4 months ago
DynEval: Holistic Evaluations of T2I Generative Models in the Wild
Paper • 2607.11199 • Published • 2
Posterior Augmented Flow Matching
Paper • 2605.00825 • Published
4KLSDB: A Large-Scale Dataset for 4K Image Restoration and Generation
Paper • 2605.24762 • Published • 1
Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models
Paper • 2607.04461 • Published • 10
sayakpaul
submitted a
paper to Daily Papers 4 months ago
Post
273
We have recently added Torch Stable ABI support to kernels and kernel-builder. This allows kernel developers to target a particular Torch version and the kernel will be supported on that Torch version and later Torch versions (up to ~2 years).
This makes it much easier to write kernels with long-term support and not just the last two Torch releases.
We have also started rolling out Stable ABI support to kernels in kernels-community, starting with Flash Attention 3, supporting Torch 2.9 and later as well as CUDA versions starting at 12.6:
https://huggingface.co/kernels/kernels-community/flash-attn3/tree/v1/build
This makes it much easier to write kernels with long-term support and not just the last two Torch releases.
We have also started rolling out Stable ABI support to kernels in kernels-community, starting with Flash Attention 3, supporting Torch 2.9 and later as well as CUDA versions starting at 12.6:
https://huggingface.co/kernels/kernels-community/flash-attn3/tree/v1/build
- 1 reply
Post
299
Two large changes in kernel-builder this week:
kernel-builder now links libstdc++ dynamically. To support a wide range of systems, we build against libstdc++ from manylinux_2_28 (EL 8 and later).
Following our Torch support policy that the current and previous Torch versions are supported, Torch 2.10 support was removed. We will soon also support the Torch stable ABI, so that it is possible to write kernels that support a large number of Torch versions.
kernel-builder now links libstdc++ dynamically. To support a wide range of systems, we build against libstdc++ from manylinux_2_28 (EL 8 and later).
Following our Torch support policy that the current and previous Torch versions are supported, Torch 2.10 support was removed. We will soon also support the Torch stable ABI, so that it is possible to write kernels that support a large number of Torch versions.
sayakpaul
authored 2
papers 8 months ago
sayakpaul
submitted a
paper to Daily Papers 8 months ago
sayakpaul
authored a
paper 9 months ago
Post
2,849
kernels 0.12 is out! 🎉
Changes:
* Support for kernel version branches to gracefully roll out kernel API changes.
* Support for PyTorch 2.10.
* kernel-builder is now merged into the kernels repo.
* Initial support for standardized kernel benchmarks.
https://github.com/huggingface/kernels/releases/tag/v0.12.0
Changes:
* Support for kernel version branches to gracefully roll out kernel API changes.
* Support for PyTorch 2.10.
* kernel-builder is now merged into the kernels repo.
* Initial support for standardized kernel benchmarks.
https://github.com/huggingface/kernels/releases/tag/v0.12.0
Post
564
We have released
Headline features:
* 🔮 Supports building kernels for the brand-new PyTorch 2.9.0.
* 🪟 Experimental support for building Windows kernels.
kernel-builder 0.7.0: https://github.com/huggingface/kernel-builder/releases/tag/v0.7.0Headline features:
* 🔮 Supports building kernels for the brand-new PyTorch 2.9.0.
* 🪟 Experimental support for building Windows kernels.
sayakpaul
authored a
paper about 1 year ago
Post
3,605
Fast LoRA inference for Flux with Diffusers and PEFT 🚨
There are great materials that demonstrate how to optimize inference for popular image generation models, such as Flux. However, very few cover how to serve LoRAs fast, despite LoRAs being an inseparable part of their adoption.
In our latest post, @BenjaminB and I show different techniques to optimize LoRA inference for the Flux family of models for image generation. Our recipe includes the use of:
1.
2. Flash Attention 3 (when compatible)
3. Dynamic FP8 weight quantization (when compatible)
4. Hotswapping for avoiding recompilation during swapping new LoRAs 🤯
We have tested our recipe with Flux.1-Dev on both H100 and RTX 4090. We achieve at least a *2x speedup* in either of the GPUs. We believe our recipe is grounded in the reality of how LoRA-based use cases are generally served. So, we hope this will be beneficial to the community 🤗
Even though our recipe was tested primarily with NVIDIA GPUs, it should also work with AMD GPUs.
Learn the details and the full code here:
https://huggingface.co/blog/lora-fast
There are great materials that demonstrate how to optimize inference for popular image generation models, such as Flux. However, very few cover how to serve LoRAs fast, despite LoRAs being an inseparable part of their adoption.
In our latest post, @BenjaminB and I show different techniques to optimize LoRA inference for the Flux family of models for image generation. Our recipe includes the use of:
1.
torch.compile2. Flash Attention 3 (when compatible)
3. Dynamic FP8 weight quantization (when compatible)
4. Hotswapping for avoiding recompilation during swapping new LoRAs 🤯
We have tested our recipe with Flux.1-Dev on both H100 and RTX 4090. We achieve at least a *2x speedup* in either of the GPUs. We believe our recipe is grounded in the reality of how LoRA-based use cases are generally served. So, we hope this will be beneficial to the community 🤗
Even though our recipe was tested primarily with NVIDIA GPUs, it should also work with AMD GPUs.
Learn the details and the full code here:
https://huggingface.co/blog/lora-fast
- 3 replies