相关论文: The OoO VLIW JIT Compiler for GPU Inference

We introduce just-in-time (JIT) compilation to the integral kernels for Gaussian-type orbitals (GTOs) to enhance the efficiency of electron repulsion integral computations. For Coulomb and exchange (JK) matrices, JIT-based algorithms yield…

This paper describes a C++ library that compiles neural network models at runtime into machine code that performs inference. This approach in general promises to achieve the best performance possible since it is able to integrate statically…

Just-in-Time (JIT) compilers are used by many modern programming systems in order to improve performance. Bugs in JIT compilers provide exploitable security vulnerabilities and debugging them is difficult as they are large, complex, and…

Dr$.$Jit is a new just-in-time compiler for physically based rendering and its derivative. Dr$.$Jit expedites research on these topics in two ways: first, it traces high-level simulation code (e.g., written in Python) and aggressively…

Computer-use agents (CUA) automate tasks specified with natural language such as "order the cheapest item from Taco Bell" by generating sequences of calls to tools such as click, type, and scroll on a browser. Current implementations follow…

Data format innovations have been critical for machine learning (ML) scaling, which in turn fuels ground-breaking ML capabilities. However, even in the presence of low-precision formats, model weights are often stored in both high-precision…

As machine learning techniques are applied to a widening range of applications, high throughput machine learning (ML) inference servers have become critical for online service applications. Such ML inference servers pose two challenges:…

Generative large language models (LLMs) have garnered significant attention due to their exceptional capabilities in various AI tasks. Traditionally deployed in cloud datacenters, LLMs are now increasingly moving towards more accessible…

Context: Just-in-Time (JIT) compilers are able to specialize the code they generate according to a continuous profiling of the running programs. This gives them an advantage when compared to Ahead-of-Time (AoT) compilers that must choose…

FPGA vendors have recently started focusing on OpenCL for FPGAs because of its ability to leverage the parallelism inherent to heterogeneous computing platforms. OpenCL allows programs running on a host computer to launch accelerator…

Web is increasingly becoming the primary platform to deliver AI services onto edge devices, making in-browser deep learning (DL) inference more prominent. Nevertheless, the heterogeneity of edge devices, combined with the underdeveloped…

Large Language Models (LLMs) have achieved strong performance across natural language and multimodal tasks, yet their practical deployment remains constrained by inference latency and kernel launch overhead, particularly in interactive,…

Modern LLM serving systems confront inefficient GPU utilization due to the fundamental mismatch between compute-intensive prefill and memory-bound decode phases. While current practices attempt to address this by organizing these phases…

This paper presents various improvements that were applied to OCamlJIT2, a Just-In-Time compiler for the OCaml byte-code virtual machine. OCamlJIT2 currently runs on various Unix-like systems with x86 or x86-64 processors. The improvements,…

As inference on Large Language Models (LLMs) emerges as an important workload in machine learning applications, weight quantization has become a standard technique for efficient GPU deployment. Quantization not only reduces model size, but…

Parallel accelerators, such as GPUs, are key enablers for large-scale Machine Learning (ML) applications. However, ML model developers often lack detailed knowledge of the underlying system architectures, while system programmers usually do…

Serving deep neural networks in latency critical interactive settings often requires GPU acceleration. However, the small batch sizes typical in online inference results in poor GPU utilization, a potential performance gap which GPU…

Highly parallelized workloads like machine learning training, inferences and general HPC tasks are greatly accelerated using GPU devices. In a cloud computing cluster, serving a GPU's computation power through multi-tasks sharing is highly…

Neural network training requires a large amount of computation and thus GPUs are often used for the acceleration. While they improve the performance, GPUs are underutilized during the training.This paper proposes out-of-order (ooo)…

Applications in emerging domains such as XR are being built as compound inference systems, where multiple ML models are composed in the form of a task graph to service each request. Serving these compound systems efficiently raises two…