Mike Lasby @mikelasby

Machine learning researcher, engineer, & enthusiast | PhD Candidate at UofC | When I'm not at the keyboard, I'm outside hiking, biking, or skiing. University of Calgary Joined November 2014

Tweets

205
Followers

115
Following

381
Likes

218

Cerebras @CerebrasSystems

a month ago

Chat app is a little slow right now. We are seeing ~3700 TPS on OpenRouter inference-docs.cerebras.ai/models/openai-…

3 3 81 8K 10

Download Image

Mike Lasby @mikelasby

a month ago

Frontier coding capabilites at the speed of light 🚀

Cerebras @CerebrasSystems

a month ago

Frontier coding capabilites at the speed of light 🚀

45 76 887 349K 237

Download Video

0 0 2 58 1

'Jonathan Ross and I made this bet in 2017. Groq is now the fastest inference solution in market' Society would expect @chamath to be truthful. I mean pick a model...any model. Look at independent benchmarks. These charts aren't hard to read.

Chamath Palihapitiya @chamath

2 months ago

44 48 324 211K 125

14 8 131 49K 27

Download Image

Dan Alistarh @DAlistarh

2 months ago

Contributors: - QuTLASS is led by @RobertoL_Castro - FP-Quant contributors @black_samorez @AshkboosSaleh @_EldarKurtic @mgoin_ as well as Denis Kuznedelev and Vage Egiazarian Code and models: - github.com/IST-DASLab/FP-… - huggingface.co/ISTA-DASLab - github.com/IST-DASLab/qut…

1 3 21 2K 5

Mike Lasby @mikelasby

2 months ago

We will be presenting Self-Distilled Sparse Drafters at #ICML this afternoon at the Efficient Systems for Foundation Models workshop. Come chat with us about acclerating speculative decoding! 🚀 @CerebrasSystems @UCalgaryML

0 4 8 288 0

Download Image

Yufan Feng @joyce_xxz

2 months ago

Having ideas on backdoor attack, functional&representational similarity, and concept-based explainability? I am looking forward to all discussions. Come visit our posters today ! 📍 TAIG at West Meeting room 109 DIG-BUGS at West Ballroom A

Yufan Feng @joyce_xxz

2 months ago

1 8 8 1K 1

Download Image

0 4 5 323 0

utku @utkuevci

2 months ago

It has been a while since I last gave a talk. I gave two lectures on compression and efficient finetuning this April at The Science and Engineering of Large Language Models Workshop organized for AIMS students. Check out the slides below: utkuevci.com/ml/aims-lectur…

2 1 10 686 2

Mohammed Adnan @adnan_ahmad1306

2 months ago

[1/2] 🧵 Presenting our work on Understanding Normalization Layers for Sparse Training today at the HiLD Workshop, ICML 2025! If you're curious about how BatchNorm & LayerNorm impact sparse networks, drop by our poster!

1 4 7 557 1

Yani Ioannou @yanii

2 months ago

We are presenting this poster at #ICML2025 today (Tues. July 15) in the first poster session 📆 11:00-13:30 in East Exhibition Hall A-B #E-2106 Drop by to learn more on why sparse training is difficult and how to reuse a mask for training from random initialization.

Mohammed Adnan @adnan_ahmad1306

4 months ago

8 27 92 21K 49

Download Image

0 1 7 282 0

Yani Ioannou @yanii

2 months ago

@UCalgaryML will be at #ICML2025 in Vancouver🇨🇦 next week: our lab has 6 different works being presented by 5 students across both the main conference & 6 workshops! We are also recruiting fully-funded ML PhD/MSc students🧑‍🎓If attending, reach out to me on Whova app to meet 📅

0 10 17 930 1

Download Image

Sukjun (June) Hwang @sukjun_hwang

2 months ago

Tokenization has been the final barrier to truly end-to-end language models. We developed the H-Net: a hierarchical network that replaces tokenization with a dynamic chunking process directly inside the model, automatically discovering and operating over meaningful units of data

98 744 5K 736K 4K

Download Gif

Wentao Guo @WentaoGuo7

2 months ago

🦆🚀QuACK🦆🚀: new SOL mem-bound kernel library without a single line of CUDA C++ all straight in Python thanks to CuTe-DSL. On H100 with 3TB/s, it performs 33%-50% faster than highly optimized libraries like PyTorch's torch.compile and Liger. 🤯 With @tedzadouri and @tri_dao

13 73 332 77K 204

Download Image

Yufan Feng @joyce_xxz

2 months ago

I am excited to share that I will present two of my works at #ICML2025 workshops! If you are interested in AI security and XAI, feel free to come by and chat - I'm looking forward to all feedbacks and discussions!

1 8 8 1K 1

Download Image

Mohammed Adnan @adnan_ahmad1306

2 months ago

Excited to be presenting our work at ICML next week! If you're interested in loss landscapes, weight symmetries, or sparse training, come check out our poster — we'd love to chat. 📍 East Exhibition Hall A-B, #E-2106. 📅 Tue, July 15 | 🕚 11:00 a.m. – 1:30 p.m PDT.

Mohammed Adnan @adnan_ahmad1306

4 months ago

8 27 92 21K 49

Download Image

0 10 16 2K 1

Cerebras @CerebrasSystems

2 months ago

Featured Paper at @icmlconf - The Internationall Conference on Machine Learning: SD² - Self-Distilled Sparse Drafters Speculative decoding is a powerful technique for reducing the latency of Large Language Models (LLMs), offering a fault-tolerant framework that enables the…

1 10 51 3K 9

Download Image

Daniil Larionov @Rexhaif

2 months ago

Looks like OpenReview had enough of these reviewers and decided to lay down :)

0 1 12 1K 0

Download Image

Mike Lasby @mikelasby

3 months ago

"Accept reality as it is, try not to regret the past, and try to improve the situation." "The challenge that AI poses is the greatest challenge of humanity ever. And overcoming will also bring the greatest reward. And in some sense, whether you like it or not, your life is going…

0 0 1 63 0

Infini-AI-Lab @InfiniAILab

3 months ago

🥳 Happy to share our new work – Kinetics: Rethinking Test-Time Scaling Laws 🤔How to effectively build a powerful reasoning agent? Existing compute-optimal scaling laws suggest 64K thinking tokens + 1.7B model > 32B model. But, It only shows half of the picture! 🚨 The O(N²)…

7 71 246 78K 163

Download Image

Lysandre @LysandreJik

3 months ago

I have bittersweet news to share. Yesterday we merged a PR deprecating TensorFlow and Flax support in transformers. Going forward, we're focusing all our efforts on PyTorch to remove a lot of the bloating in the transformers library. Expect a simpler toolkit, across the board.