@tallamjr Profile picture

Tarek Allam Jr, PhD

@tallamjr

⚙️Lead Research Engineer @turinginst & Research Engineering Fellow @SoftwareSaved 💻 #compression , #edgeAI & #tinyML aficionado 🗜

Similar User
Claire Vedette photo

@Claire_Vedette

Uddeshya Upadhyay photo

@uddupa

Awais photo

@deepawais

Esteban Blanc 🐧 photo

@Skallwar

Christina Last photo

@last_christina

Ed Chalstrey photo

@EChalstrey

🔸Michael Huet🔸 🇬🇧🇦🇺🇪🇺🏳️‍🌈 photo

@MichaelJHuet

Paulo Cotta photo

@PauloVPCotta

GDvisuals photo

@GDvisuals

Sandeep Banerjee photo

@_ml_fanatic

Tarek Allam Jr, PhD Reposted

In our recent paper accepted at NeurIPS 2024, my student, Rachel Si Yan Teo (@rachtsy_), uncovered a link between self-attention in transformers and kernel PCA. Specifically, Rachel demonstrates that self-attention projects its query vectors onto the principal component axes of…

Tweet Image 1

Tarek Allam Jr, PhD Reposted

On-device AI framework ecosystem is blooming these days: 1. llama.cpp - All things Whisper, LLMs & VLMs - run across Metal, CUDA and other backends (AMD/ NPU etc) github.com/ggerganov/llam… 2. MLC - Deploy LLMs across platforms especially WebGPU (fastest WebGPU LLM implementation…


Tarek Allam Jr, PhD Reposted

Today, we're shipping a series of features that move uv beyond a pip alternative, and into an end-to-end solution for managing Python projects, command-line tools, single-file scripts, and even Python itself. A single, unified tool. Like Cargo, for Python. It's very fast.

Tweet Image 1

Tarek Allam Jr, PhD Reposted

🤗 x Polars! Polars now supports native reading from @huggingface datasets. Check out our latest blog to learn more about it: pola.rs/posts/polars-h…


Tarek Allam Jr, PhD Reposted

TinyTrain allows *learning* not just inference to be performed on MCUs in a compute-, memory- and data-efficient manner! Young and other co-authors are at #ICML2024, reach out to chat. TinyTrain work by @YoungDKwon1, @ruiruiliii, @SIVenieris, @jag_jagmohan, @niclane7 and @cecim


Tarek Allam Jr, PhD Reposted

The first beta pre-release of Polars 1.0 is released! Install it with `pip install -U --pre polars ` and give it a spin. If you find any troubles in the coming week, we can fix them for 1.0. Release notes: github.com/pola-rs/polars… The upgrade guide will follow later next week.


Tarek Allam Jr, PhD Reposted

Hugging face just merged Polars integration 🐻‍❄️

Rust 🦀 is sooo fast for querying data :o We just merged support for Polars and it's a blast ! Explore any dataset on 🤗 at ⚡ speed:

Tweet Image 1


Tarek Allam Jr, PhD Reposted

Check out our new article about Google's growth in Rust usage during 2022! We debunk some common myths about Rust and share our experiences. Spoiler alert: it's faster to learn than you think, and the productivity and code quality are amazing! #rustlang opensource.googleblog.com/2023/06/rust-f…


Tarek Allam Jr, PhD Reposted

Proceedings PDFs for @icmlconf accepted papers are now available on OpenReview: openreview.net/group?id=ICML.… #ICML2023

The list of accepted papers for @icmlconf is now visible here: icml.cc/virtual/2023/p… #ICML2023



Tarek Allam Jr, PhD Reposted

Want to train your own Bark/MusicGen-like TTS/TTA models? 👀 The SoTA Encodec model by @MetaAI has now landed in 🤗Transformers! It supports compression up to 1.5KHz and produces discrete audio representations. ⚡️ Model: huggingface.co/docs/transform… Colab: github.com/Vaibhavs10/not…


Tarek Allam Jr, PhD Reposted

Run 13B model on an iPhone! 🤯 Just finished reading @Tim_Dettmers’ amazing work on SpQR. SpQR unlocks 3.35 bit quantisation which lets us run 33B models on 3090s and 13B models on an iPhone. Here are my notes from the paper: - Quantisation is basically like compressing the…

Tweet Image 1

Tarek Allam Jr, PhD Reposted

The 2nd iteration of the "Neural Compression: From Information Theory to Applications" workshop will take place @icmlconf in Hawaii this year! Submissions due May 27th. For more details:neuralcompression.github.io/workshop23 @BerivanISIK @YiboYang @_dsevero @karen_ullrich @robamler @s_mandt


Tarek Allam Jr, PhD Reposted

New blog post on @DataPolars: the output from .unique is no longer set by the order of the input. Don't let it take you by surprise! In this post I explore what happens, what's changed and why things work the way they do: rhosignal.com/posts/polars-o…


Tarek Allam Jr, PhD Reposted

Deadline for abstracts is today! Come share your work and perspectives for transient and variable astronomy in the era of Rubin!

OzFink workshop abstracts are open! Join us on May 3-5 to explore the amazing potential of @VRubinObs time-domain astronomy with the @FinkBroker and the Australian community! ozgrav.org/ozfink-worksho… kilonovae, anomalies, supernovae, SSO, multi-wavelength data and so much more!



Tarek Allam Jr, PhD Reposted

#Python #polars 0.14.27 is released. github.com/pola-rs/polars… This release launches the alpha version of our streaming engine. Need to process 250GB on you laptop? Try: my_query().collect(allow_streaming=True) Next we release we will be able to | the result to different files!


Tarek Allam Jr, PhD Reposted

Applying to become a @SoftwareSaved Fellow was one of the best decisions of my career: it is such an amazing community that cares deeply about open research practices, software in and as research, and rewarding software/data aligned careers. If you like all that, do take a look.

OzFink workshop abstracts are open! Join us on May 3-5 to explore the amazing potential of @VRubinObs time-domain astronomy with the @FinkBroker and the Australian community! ozgrav.org/ozfink-worksho… kilonovae, anomalies, supernovae, SSO, multi-wavelength data and so much more!



Tarek Allam Jr, PhD Reposted

Statistical Rethinking 2022 Complete Course is complete. 20 lectures from foundations of causal & Bayesian inference through DAGS, multilevel models & poststratified causal effects to Gaussian processes, Bayesian imputation & ODEs. Theatrical trailer: youtube.com/watch?v=BYUykH…


Tarek Allam Jr, PhD Reposted

Interested in converting the theory of "Probabilistic Machine Learning: Advanced Topics" into beautiful #JAX code? Available to work this summer? Consider applying to #GSoC. Details at github.com/probml/pyprobm…

Tweet Image 1

Tarek Allam Jr, PhD Reposted

Today in @nature, with @EPFL, the first deep reinforcement learning system that can keep nuclear fusion plasma stable inside its tokamaks, opening new avenues to advance nuclear fusion research. Paper: dpmd.ai/fusion-paper


Tarek Allam Jr, PhD Reposted

DietGPU: Extremely fast lossless data compression on GPUs using ANS. Target applications include training in HPC settings where it is desirable to reduce interconnect bandwidth at the cost of compute. Authored by Jeff Johnson at Meta. github.com/facebookresear…


Loading...

Something went wrong.


Something went wrong.