Related papers: HiveMind: OS-Inspired Scheduling for Concurrent LL…

With the rapid advancement of large language models (LLMs), efficiently serving LLM inference under limited GPU resources has become a critical challenge. Recently, an increasing number of studies have explored applying serverless computing…

Efficient scheduling of LLM inference tasks is essential for achieving low latency and high throughput, particularly with the growing use of reasoning-capable LLMs. Traditional strategies like First-Come-First-Serve (FCFS) often suffer from…

The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe…

Large language models(LLMs) are now used to power complex multi-turn agentic workflows. Existing systems run agentic inference by loosely assembling isolated components: an LLM inference engine (e.g., vLLM) and a tool orchestrator (e.g.,…

Recent advances in LLM-based Text-to-SQL have achieved remarkable gains on public benchmarks such as BIRD and Spider. Yet, these systems struggle to scale in realistic enterprise settings with large, complex schemas, diverse SQL dialects,…

Manual software beta testing is costly and time-consuming, while single-agent large language model (LLM) approaches suffer from hallucinations and inconsistent behavior. We propose a multi-agent committee framework in which diverse…

The rapid shift from stateless large language models (LLMs) to autonomous, goal-driven agents raises a central question: When is agentic AI truly necessary? While agents enable multi-step reasoning, persistent memory, and tool…

In this report, we propose Triton-distributed, an extension of existing Triton compiler, to overcome the programming challenges in distributed AI systems. Triton-distributed is the first compiler that supports native overlapping…

Hybrid parallelism underpins large-scale LLM training across tens of thousands of GPUs. At such scale, hardware failures on individual devices lead to performance skew across devices, diminishing overall training efficiency. Existing…

Batch inference for agentic workloads stresses the GPU key-value (KV) cache in a sustained and cumulative manner, often causing severe throughput degradation well before memory capacity is exhausted. We identify this phenomenon as…

Large language model (LLM) applications are evolving beyond simple chatbots into dynamic, general-purpose agentic programs, which scale LLM calls and output tokens to help AI agents reason, explore, and solve complex tasks. However,…

Large Language Models (LLMs) are increasingly being deployed as the reasoning engines for agentic AI systems, yet they exhibit a critical flaw: a rigid adherence to explicit rules that leads to decisions misaligned with human common sense…

LLM-based coding agents rely on \emph{skills}, pre-packaged instruction sets that extend agent capabilities, yet every token of skill content injected into the context window incurs both monetary cost and attention dilution. To understand…

Hosting diverse large language model workloads in a unified resource pool through co-location is cost-effective. For example, long-running chat services generally follow diurnal traffic patterns, which inspire co-location of batch jobs to…

Large Language Models (LLMs) are increasingly being deployed in applications such as chatbots, code editors, and conversational agents. A key feature of LLMs is their ability to engage in multi-turn interactions with humans or external…

Modern software engineers operate across 5-10 disconnected tools daily: GitHub, GitLab, Jira, Slack, calendar applications, CI dashboards, AI coding assistants, and container platforms. This fragmentation creates cognitive overhead that…

Current LLM agents operate under an implicit but universal assumption: execution is a transaction -- the user submits a request, the agent works in isolation, and only upon completion does the dialogue resume. This forces users into a…

Automatic code optimization remains a difficult challenge, particularly for complex loop nests on modern hardware. This paper investigates a novel approach to code optimization where Large Language Models (LLMs) guide the process through a…

Running language models in the browser presents a unique opportunity to build efficient, private, and portable AI applications, but requires contending with constrained memory availability and heterogeneous hardware targets. To realize this…

Multi-agent LLM systems have become the dominant production workload, but the serving stack was not built for them. The agent framework above knows agent identities, role, schemas, and dispatch structure but never sees an engine-level…