Starcoder 2 and the stack v2: The next generation
The BigCode project, an open-scientific collaboration focused on the responsible
development of Large Language Models for Code (Code LLMs), introduces StarCoder2. In …
development of Large Language Models for Code (Code LLMs), introduces StarCoder2. In …
Meta large language model compiler: Foundation models of compiler optimization
Large Language Models (LLMs) have demonstrated remarkable capabilities across a
variety of software engineering and coding tasks. However, their application in the domain of …
variety of software engineering and coding tasks. However, their application in the domain of …
Domain-Specific Code Language Models: Unraveling the Potential for HPC Codes and Tasks
With easier access to powerful compute resources, there is a growing trend in AI for software
development to develop larger language models (LLMs) to address a variety of …
development to develop larger language models (LLMs) to address a variety of …
Input-Gen: Guided Generation of Stateful Inputs for Testing, Tuning, and Training
The size and complexity of software applications is increasing at an accelerating pace.
Source code repositories (along with their dependencies) require vast amounts of labor to …
Source code repositories (along with their dependencies) require vast amounts of labor to …
Optimistic and Scalable Global Function Merging
K Lee, M Ren, E Hoag - Proceedings of the 25th ACM SIGPLAN/SIGBED …, 2024 - dl.acm.org
Function merging is a pivotal technique for reducing code size by combining identical or
similar functions into a single function. While prior research has extensively explored this …
similar functions into a single function. While prior research has extensively explored this …
Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization
TV Marinov, A Agarwal, M Trofin - arxiv preprint arxiv:2403.19462, 2024 - arxiv.org
This work studies a Reinforcement Learning (RL) problem in which we are given a set of
trajectories collected with K baseline policies. Each of these policies can be quite …
trajectories collected with K baseline policies. Each of these policies can be quite …
Optimistic Global Function Merger
K Lee, M Ren, E Hoag - arxiv preprint arxiv:2312.03214, 2023 - arxiv.org
Function merging is a pivotal technique for reducing code size by combining identical or
similar functions into a single function. While prior research has extensively explored this …
similar functions into a single function. While prior research has extensively explored this …
Assurance of Reasoning Enabled Systems (ARES)
A Marquez, TC Fujimoto, TJ Stavenger - 2024 - osti.gov
ARES was in part motivated by the determination of President's Council of Advisors on
Science and Technology (PCAST) on May 13th, 2023 that published a set of inquiries: In an …
Science and Technology (PCAST) on May 13th, 2023 that published a set of inquiries: In an …
[PDF][PDF] Scalable RL for Systems via Offline Imitation from Multiple Baselines: A Case Study in Compiler Optimization
TV Marinov, A Agarwal, M Trofin - mlforsystems.org
From scheduling, to resource allocation to optimization of complex workflows, systems are
replete with decision-making problems which are typically addressed with hand-designed …
replete with decision-making problems which are typically addressed with hand-designed …