Tianqi Chen (@tqchenml) / X

Tianqi Chen

1,657 posts

Tianqi Chen

@tqchenml

AssistProf @CarnegieMellon. Distinguished Eng @NVIDIA. Creator of @XGBoostProject, @ApacheTVM. Member catalyst.cs.cmu.edu, @TheASF. Views are on my own

CMU

Joined May 2015

Pinned
Tianqi Chen
@tqchenml
Jun 7, 2024
Exciting to share we have been working on over the past one year. MLCEngine, a universal LLM deployment engine that brings the power of server optimizations and local deploymet into a single framework, checkout platforms support 👇 and blogpost blog.mlc.ai/2024/06/07/uni… more in a🧵
62K
Tianqi Chen
@tqchenml
Jun 15, 2019
I will join @mldcmu and @CSDatCMU @SCSatCMU in Fall 2020 as an Assistant Professor. I am super grateful to my advisors, collaborators and @uwcse for a wonderful PhD journey. Looking forward to working with colleagues on more cross-stack research for future intelligent systems.
Tianqi Chen
@tqchenml
Aug 26, 2025
The new semester is here at CMU, excited to co-teach with @Tim_Dettmers , to offer our fun course again on "Build Your Mini-PyTorch (needle) from scratch, then build neural networks on top". (Deep Learning Systems) Check out dlsyscourse.org to learn more
Deep Learning Systems
From dlsyscourse.org
37K
Tianqi Chen
@tqchenml
Dec 16, 2023
Chat with Mistral 7B Instruct v0.2 running locally in iphone and ipad. Now available in @AppStore. apps.apple.com/gb/app/mlc-cha…
00:00
135K
Tianqi Chen
@tqchenml
Apr 29, 2023
Running LLM-based chat locally on iphone 📱with GPU acceleration. Also brings universal deployment to NV/AMD/M1 GPUs. Love to see it enabling personal assistants for everyone. Try out demos mlc.ai/mlc-llm/
GIF
Bohan Hou
@bohanhou1998
Apr 29, 2023
Can LLMs run natively on your iPhone📱? Our answer is yes, and we can do more! We are introducing MLC-LLM, an open framework that brings language models (LLMs) directly into a broad class of platforms (CUDA, Vulkan, Metal) with GPU acceleration! Demo: mlc.ai/mlc-llm/
100K
Tianqi Chen
@tqchenml
Jun 4, 2023
MLC Chat app is now on @AppStore Checkout it out! Chat with open language models running on your iPad and iPhone, offline, locally, no data collected apps.apple.com/us/app/mlc-cha…
101K
Tianqi Chen
@tqchenml
Oct 6, 2017
Introducing NNVM compiler tvmlang.org/2017/10/06/nnv… brings MXNet, PyTorch, Caffe2, CoreML to bare-metal hardware backends with #TVM stack
Allen School
@uwcse
Oct 6, 2017
#UWAllen researchers team up with @awscloud to release new NNVM compiler for deep learning frameworks: news.cs.washington.edu/2017/10/06/all…
Tianqi Chen
@tqchenml
Aug 28, 2024
The new semester is here, and one thing that excites me is working with fresh faces and having fun again on our deep learning systems course with @zicokolter, where we built a mini-PyTorch (needle) from scratch and use it to build deep learning models.
Deep Learning Systems
From dlsyscourse.org
37K
Tianqi Chen
@tqchenml
Jun 2, 2022
A summer endeavor, developing MLC: the first open lecture series on ML compilation. Machine learning compilation is an emerging field for systematic optimization and deployment of AI workloads. Hope to share adventures and fun with the community mlc.ai/summer22/ 🚀
Tianqi Chen
@tqchenml
Mar 12, 2018
Compile your deep learning models directly into WebGL and deploy to browsers without having to write a single line of javascript! tvmlang.org/2018/03/12/web…
Tianqi Chen
@tqchenml
Jan 3, 2025
Are you curious about how to build an efficient and customizable attention engine bebind the scene of major LLM serving frameworks? Checkout the latest arxiv paper on FlashInfer about all the cool ideas arxiv.org/abs/2501.01005 from @ye_combinator
arxiv.org
FlashInfer: Efficient and Customizable Attention Engine for LLM...
Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput...
18K
Tianqi Chen
@tqchenml
Nov 22, 2024
🚀Future LLM agents speak JSON, python, and other structures. Excited to announce XGrammar, an structured generation library that enables zero-overhead structure constraining. Bring 2x-10x speedup in grammar guided LLM serving. Checkout github repo, blog to learn more 👉
44K
Tianqi Chen
@tqchenml
May 1, 2023
Today LLMs require extensive computation and memory to run and usually run on servers. What will be the future of consumer devices in the era of AI? While it is hard to predict the future, let us talk about possible opportunities and how we can enable them mlc.ai/blog/blog/2023…
34K
Tianqi Chen
@tqchenml
Sep 22, 2022
Autodiff is the backbone of DL frameworks. In Lecture 4 of open DLSysCourse, we derive auto-diff from scratch and bring it further under the context of architecture considerations in frameworks such as @PyTorch and @TensorFlow. Checkout youtu.be/56WUlMEeAuA to learn more