Hugging Face's logo
Régis Pierrard's picture
68 4 12

Régis Pierrard

regisss
orion-penner's profile picture Bellamy66's profile picture yafshar's profile picture
·

AI & ML interests

None yet

Recent Activity

liked a Space 1 day ago
nanotron/ultrascale-playbook
posted an update 7 days ago
Nice paper comparing the fp8 inference efficiency of Nvidia H100 and Intel Gaudi2: https://huggingface.co/papers/2502.01070 The conclusion is interesting: "Our findings highlight that the Gaudi 2, by leveraging FP8, achieves higher throughput-to-power efficiency during LLM inference" One aspect of AI hardware accelerators that is often overlooked is how they consume less energy than GPUs. It's nice to see researchers starting carrying out experiments to measure this! Gaudi3 results soon...
upvoted a paper 8 days ago
An Investigation of FP8 Across Accelerators for LLM Inference
View all activity

Organizations

Hugging Face's profile picture Habana AI's profile picture Hugging Face Optimum's profile picture group2's profile picture Hugging Face H4's profile picture Hugging Face OSS Metrics's profile picture HuggingFace Doc Builds's profile picture Blog-explorers's profile picture AI Energy Score's profile picture Social Post Explorers's profile picture Hugging Face Machine Learning Optimization's profile picture Optimum Internal Testing's profile picture SLLHF's profile picture Privacy Preserving AI Hackathon (Zama, Hugging Face, Entrepreneur First)'s profile picture

regisss's activity

upvoted a paper 8 days ago
upvoted an article about 1 month ago
view article
Article

Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference

• 68
upvoted an article 4 months ago
view article
Article

Organizing a Privacy-preserving Hackathon

By binoua and 1 other •
• 8
upvoted an article 10 months ago