39 citations · 48 across the 9 of their papers we have counts for
10 papers
Self-Orchestrating Language Models: Leveraging Semantic Dependence for Efficient Inference
Tian Jin
Large language models (LLMs) demonstrate impressive capabilities, but their deployment presents significant efficiency challenges. Autoregressive decoding imposes substantial infer…
Planned Diffusion
Daniel Israel, Tian Jin, Ellie Cheng +4
Most large language models are autoregressive: they generate tokens one at a time. Discrete diffusion language models can generate multiple tokens in parallel, but sampling from th…
Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding
Tian Jin, Ellie Y. Cheng, Zack Ankner +6
Decoding with autoregressive large language models (LLMs) traditionally occurs sequentially, generating one token after another. An emerging line of work explored parallel decoding…
The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
Tian Jin, Ahmed Imtiaz Humayun, Utku Evci +4
Pruning eliminates unnecessary parameters in neural networks; it offers a promising solution to the growing computational demands of large language models (LLMs). While many focus…
Self-Selected Attention Span for Accelerating Large Language Model Inference
Tian Jin, Wanzin Yazar, Zifei Xu +2
Large language models (LLMs) can solve challenging tasks. However, their inference computation on modern GPUs is highly inefficient due to the increasing number of tokens they must…
Striped Attention: Faster Ring Attention for Causal Transformers
William Brandon, Aniruddha Nrusimha, Kevin Qian +4
To help address the growing demand for ever-longer sequence lengths in transformer models, Liu et al. recently proposed Ring Attention, an exact attention algorithm capable of over…
Pruning's Effect on Generalization Through the Lens of Training and Regularization
Tian Jin, Michael Carbin, Daniel M. Roy +2
Practitioners frequently observe that pruning improves model generalization. A long-standing hypothesis based on bias-variance trade-off attributes this generalization improvement…
Efficient Automatic Scheduling of Imaging and Vision Pipelines for the GPU
Luke Anderson, Andrew Adams, Karima Ma +3
We present a new algorithm to quickly generate high-performance GPU implementations of complex imaging and vision pipelines, directly from high-level Halide algorithm code. It is f…
Compiling ONNX Neural Network Models Using MLIR
Tian Jin, Gheorghe-Teodor Bercea, Tung D. Le +8
Deep neural network models are becoming increasingly popular and have been used in various tasks such as computer vision, speech recognition, and natural language processing. Machi…
Hybrid Static/Dynamic Schedules for Tiled Polyhedral Programs
Tian Jin, Nirmal Prajapati, Waruna Ranasinghe +4
Polyhedral compilers perform optimizations such as tiling and parallelization; when doing both, they usually generate code that executes "barrier-synchronized wavefronts" of tiles.…