Search Results for author:
Found 10 papers, 5 papers with code
Efficiently Programming Large Language Models using SGLang
SGLang is designed for the efficient programming of LLMs and incorporates primitives for common LLM programming patterns.
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.
RAF: Holistic Compilation for Deep Learning Model Training
In this paper, we present RAF, a deep learning compiler for training.
Slapo: A Schedule Language for Progressive Optimization of Large Deep Learning Model Training
Specifically, Slapo works on a PyTorch model and uses a set of schedule primitives to convert the model for common model training optimizations such as high-performance kernels, effective 3D parallelism, and efficient activation checkpointing.
Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs
With the proposed paradigm, we implement a deep learning compiler Hidet.
TensorIR: An Abstraction for Automatic Tensorized Program Optimization
Finally, we build an end-to-end framework on top of our abstraction to automatically optimize deep learning models for given tensor computation primitives.
Tensor Program Optimization with Probabilistic Programs
Experimental results show that MetaSchedule can cover the search space used in the state-of-the-art tensor program optimization frameworks in a modular way.
Bring Your Own Codegen to Deep Learning Compiler
Deep neural networks (DNNs) have been ubiquitously applied in many applications, and accelerators are emerged as an enabler to support the fast and efficient inference tasks of these applications.
Ansor: Generating High-Performance Tensor Programs for Deep Learning
Ansor can find high-performance programs that are outside the search space of existing state-of-the-art approaches.
AutoAccel: Automated Accelerator Generation and Optimization with Composable, Parallel and Pipeline Architecture
Such a well-defined template is able to support efficient accelerator designs for a broad class of computation kernels, and more importantly, drastically reduce the design space.
Distributed, Parallel, and Cluster Computing Hardware Architecture
