Dr. Kaoutar El Maghraoui

On an exciting journey to define the future of AI acceleration! AI Hardware Composer launches on two-year anniversary of IBM AI Hardware Center ibm.com/blogs/research… #ibmresearch #ibm #aihw #ai #deeplearning

Just published my new site using Manus. Click the link below to explore. kaoutarelmaghraoui.com

Instead of watching Netflix, watch this interview of Anthropic’s CEO

Apple's WWDC24 reactions and mechanistic interpretability youtu.be/_bCsW_Jrcts?si… via @YouTube

This is really a 'WOW' paper. 🤯 Claims that MatMul operations can be completely eliminated from LLMs while maintaining strong performance at billion-parameter scales and by utilizing an optimized kernel during inference, their model’s memory consumption can be reduced by more than 10× compared to unoptimized models. 🤯 'Scalable MatMul-free Language Modeling' Concludes that it is possible to create the first scalable MatMul-free LLM that achieves performance on par with state-of-the-art Transformers at billion-parameter scales. 📌 The proposed MatMul-free LLM replaces MatMul operations in dense layers with ternary accumulations using weights constrained to {-1, 0, +1}. This reduces computational cost and memory utilization while preserving network expressiveness. 📌 To remove MatMul from self-attention, the Gated Recurrent Unit (GRU) is optimized to rely solely on element-wise products, creating the MatMul-free Linear GRU (MLGRU) token mixer. The MLGRU simplifies the GRU by removing hidden-state related weights, enabling parallel computation, and replacing remaining weights with ternary matrices. 📌 For MatMul-free channel mixing, the Gated Linear Unit (GLU) is adapted to use BitLinear layers with ternary weights, eliminating expensive MatMuls while maintaining effectiveness in mixing information across channels. 📌 The paper introduces a hardware-efficient fused BitLinear layer that optimizes RMSNorm and BitLinear operations. By fusing these operations and utilizing shared memory, training speed improves by 25.6% and memory consumption reduces by 61% over an unoptimized baseline. 📌 Experimental results show that the MatMul-free LLM achieves competitive performance compared to Transformer++ baselines on downstream tasks, with the performance gap narrowing as model size increases. The scaling law projections suggest MatMul-free LLM can outperform Transformer++ in efficiency and potentially in loss when scaled up. 📌 A custom FPGA accelerator is built to exploit the lightweight operations of the MatMul-free LLM. The accelerator processes billion-parameter scale models at 13W beyond human-readable throughput, demonstrating the potential for brain-like efficiency in future lightweight LLMs.

@jacksonhinklle Hedge's letter to the children in Gaza.

Check out our newly published work about the open-source Toolkit for In-memory computing: Using the IBM analog in-memory hardware acceleration kit for neural network training and inference pubs.aip.org/aip/aml/articl…

Congratulations to senior Zayneb Cherif for helping to publish a journal article and for presenting today at the 6th IBM/IEEE AI Compute Symposium! Thank you to IBM for allowing many of our sophomores to attend the event. @YHSDeGennaro @GOLLISZJOHN @RonHattar @CMillerYorktown

Congrats to @YClassof2024 Zayneb Cherif for achieving 3rd place at recent IBM/IEEE AI Compute Symposium Poster Session. Zayneb is a member of our @YHSSciRes program under the direction of our outstanding educators Mr. Rubeo & Mr. Seweryn.🌽🏆 @GOLLISZJOHN @earthscifanatic

🌟Exciting #sponsorship Opportunity ! Join @MoroccoAI and @AlAkhawayn in their 1st AI #SummerSchool to foster innovation & connect with exceptional talents shaping the future of #AI. 📧contact@morocco.ai 🔗summerschool.morocco.ai/sponsors 🤝Let's make this a success !

Join @MoroccoAI for the AI Summer School at @AlAkhawayn University from July 17-21, 2023. Learn from renowned speakers, apply by June 23 👉summerschool.morocco.ai/application. Follow us for updates. #AISummerSchool2023 #AIEducation 🔥🌟🎓

The distinguished speakers are excited to share their latest work and mentor the participants throughout the 5-day immersive program. Get ready to be inspired! @kaoutarTech @SalimChemlal @redouanelg @mrm8488 @TariqDaouda @KhalilMrini @bouchra_bouqata @melbayad @MouradGridach🚀

discovering Islam at the WORLD CUP in QATAR 🇶🇦⚽️ youtu.be/PCDez7XB3Rs via @YouTube

We are the believers ♥️♥️🇲🇦 #WorldCup2022 #المغرب_اسبانيا

An appreciation Tweet for the 31-year-old Morocco Goalkeeper, Yassine Bounou Bono. Stopper!

IBM Quantum Summit 2022 kicks off tomorrow morning at 9:00am ET in New York City. Stay tuned for some major quantum announcements from our annual flagship event.

Construction has started on the IBM Quantum System on our main campus. It will be the first quantum computer in healthcare, aimed at accelerating the pace of medical research. Read more about our partnership with @IBMResearch: cle.clinic/3CEERUt

BREAKING 🚨: Jupiter is now at its closest to Earth since 1963, and it won't be this close for another 107 years

Sept 28: 9AM-10:30AM ET = @SSUNGA_77. Rapid-fire lightening talks w/11 amazing #womenintech & rock star ally @abdulndigital. Don't miss our @UN General Assembly 77 Science Summit interventions! Register now & be there! eventbrite.be/e/science-summ…

@JessicaSchrouff @adjiboussodieng @andrewgwils @NeurIPSConf Hi Jessica, have the decisions about the neurips tutorials been put? The website shows that they are supposed to be release yesterday.

With @adjiboussodieng and @andrewgwils, we detail some of the considerations for this year's @NeurIPSConf tutorials in this blog: blog.neurips.cc/2022/04/28/des… We are looking forward to your feedback and your submissions!