Abdennacer Badaoui

badaoui's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a Space 3 days ago

Running

133

Evaluation Guidebook

📝

133

Display evaluation metrics for LLM benchmarks

upvoted an article 5 days ago

view article

Article

Transformers v5: Simple model definitions powering the AI ecosystem

• 
• 
• +2

6 days ago

•

223

liked a Space 10 days ago

Sleeping

1

Tcid

👁

1

A dashboard

upvoted 2 articles 12 days ago

view article

Article

Continuous batching from first principles

• 
• 
• +1

12 days ago

•

241

view article

Article

Building Deep Research: How we Achieved State of the Art

• 

12 days ago

•

17

upvoted an article 17 days ago

view article

Article

Google Cloud C4 Brings a 70% TCO improvement on GPT OSS with Intel and Hugging Face

• 
• 
• +2

Oct 16

•

18

upvoted an article 18 days ago

view article

Article

Join the AMD Open Robotics Hackathon

• 

23 days ago

•

9

New activity in transformers-community/transformers-ci-dashboard 19 days ago

Fix historical data not updating after automatic reloads

#9 opened 19 days ago by

badaoui

updated a Space 19 days ago

Sleeping

1

Tcid

👁

1

A dashboard

commented on Easily Build and Share ROCm Kernels with Hugging Face 19 days ago

view reply

Yes, absolutely!
You can find the documentation for Apple Silicon (Metal) here: https://github.com/huggingface/kernel-builder/blob/main/docs/metal.md
And here’s an example of a kernel built for Metal: https://huggingface.co/kernels-community/gpt-oss-metal-kernels

posted an update 20 days ago

view post

Post

358

Building high-performance, reproducible kernels for AMD ROCm just got a lot easier.

I've put together a guide on building, testing, and sharing ROCm-compatible kernels using the Hugging Face kernel-builder and kernels libraries; so you can focus on optimizing performance rather than spending time on setup.

Learn how to:

- Use Nix for reproducible builds
- Integrate kernels as native PyTorch operators
- Share your kernels on the Hub for anyone to use with kernels.get_kernel()

We use the 🏆 award-winning RadeonFlow GEMM kernel as a practical example.

📜 Check out the full guide here : https://huggingface.co/blog/build-rocm-kernels

See translation

🔥

1

1

🤗

1

1

+

Reply

upvoted an article 20 days ago

view article

Article

Easily Build and Share ROCm Kernels with Hugging Face

• 
• 
• +2

20 days ago

•

33

published an article 20 days ago

view article

Article

Easily Build and Share ROCm Kernels with Hugging Face

• 
• 
• +2

20 days ago

•

33

upvoted an article 24 days ago

view article

Article

Building for an Open Future - our new partnership with Google Cloud

• 
• 

24 days ago

•

45

New activity in transformers-community/transformers-ci-dashboard 25 days ago

Fix data loading

#8 opened 25 days ago by

badaoui

liked a Space 25 days ago

Running

2

Kernels Benchmarks

⏲

2

Manage and navigate through HTML content within an iframe

updated a Space about 1 month ago

Running

1

Neuron Exporter

⚡

1

Export HF models to AWS Neuron-optimized format for Trn/Inf

New activity in microsoft/deberta-v3-large about 1 month ago

Add link to Neuron-optimized version

#14 opened about 1 month ago by

badaoui

updated a model about 1 month ago

badaoui/microsoft-deberta-v3-large-neuron

Fill-Mask • Updated Nov 5 • 2

published a model about 1 month ago

badaoui/microsoft-deberta-v3-large-neuron

Fill-Mask • Updated Nov 5 • 2