Search Results for author:
Found 17 papers, 14 papers with code
Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference.
Fairness in Serving Large Language Models
High-demand LLM inference services (e. g., ChatGPT and BARD) support a wide range of requests from short chat conversations to long document reading.
LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
Studying how people interact with large language models (LLMs) in real-world scenarios is increasingly important due to their widespread use in various applications.
Efficient Memory Management for Large Language Model Serving with PagedAttention
On top of it, we build vLLM, an LLM serving system that achieves (1) near-zero waste in KV cache memory and (2) flexible sharing of KV cache within and across requests to further reduce memory usage.
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences.
Ranked #3 on
Long-Context Understanding
on Ada-LEval (TSort)
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
As a result, when running OPT-175B on a single 16GB GPU, FlexGen achieves significantly higher throughput compared to state-of-the-art offloading systems, reaching a generation throughput of 1 token/s for the first time with an effective batch size of 144.
AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving
Model parallelism is conventionally viewed as a method to scale a single large deep learning model beyond the memory limits of a single device.
On Optimizing the Communication of Model Parallelism
This pattern emerges when the two paradigms of model parallelism - intra-operator and inter-operator parallelism - are combined to support large models on large clusters.
Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning
Existing model-parallel training systems either require users to manually create a parallelization plan or automatically generate one from a limited space of model parallelism configurations.
TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
With this key idea, we design TeraPipe, a high-performance token-level pipeline parallel algorithm for synchronous model-parallel training of Transformer-based language models.
Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference.
Hoplite: Efficient and Fault-Tolerant Collective Communication for Task-Based Distributed Systems
Task-based distributed frameworks (e. g., Ray, Dask, Hydro) have become increasingly popular for distributed applications that contain asynchronous and dynamic workloads, including asynchronous gradient descent, reinforcement learning, and model serving.
Fast Structured Decoding for Sequence Models
However, these models assume that the decoding process of each token is conditionally independent of others.
Hint-Based Training for Non-Autoregressive Machine Translation
Due to the unparallelizable nature of the autoregressive factorization, AutoRegressive Translation (ART) models have to generate tokens sequentially during decoding and thus suffer from high inference latency.
Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View
In this paper, we provide a novel perspective towards understanding the architecture: we show that the Transformer can be mathematically interpreted as a numerical Ordinary Differential Equation (ODE) solver for a convection-diffusion equation in a multi-particle dynamic system.
Hint-based Training for Non-Autoregressive Translation
To improve the accuracy of NART models, in this paper, we propose to leverage the hints from a well-trained ART model to train the NART model.
Towards Binary-Valued Gates for Robust LSTM Training
Long Short-Term Memory (LSTM) is one of the most widely used recurrent structures in sequence modeling.
