Abdennacer Badaoui
@abdennacer0
Followers
20
Following
165
Media
2
Statuses
8
ML Engineer 🤗 @Huggingface | Inference optimization in Transformers
Joined May 2025
Why are vLLM and transformers so damn fast? ⚡ Continuous batching. That's the secret sauce 🔥 Never heard of it? We just dropped a blog post building it up from first principles 🤗 See what happens inside the minds of the engineers pushing inference to the edge đź§
4
33
192
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!
0
0
0
Building high-performance, reproducible kernels for AMD ROCm just got a lot easier. I've put together a guide on building, and sharing ROCm-compatible kernels using Hugging Face; so you can focus on optimizing performance rather than spending time on setup. Link in the thread.
2
5
10
After ~4 years building SOTA models & datasets, we're sharing everything we learned in ⚡The Smol Training Playbook We cover the full LLM cycle: designing ablations, choosing an architecture, curating data, post-training, and building solid infrastructure. We'll help you
36
161
1K
⚡ With ONNX export, you can run your favorite models faster and more efficiently across different hardware backends, making deployment and experimentation much smoother. 💡 Have a model you’d love to see supported? Contributions are super welcome; let’s make Optimum even better.
0
0
0
🚀 Optimum libraries keep growing, and Optimum v2 is just around the corner! I recently added ONNX export support for a bunch of new models in the optimum-onnx library, including: DeepSeek-V3, Cohere, Nemotron, Arcee, StableLM … and more!
2
0
2