Copertina

Optimizing Agentic Language Model Inference via Speculative Tool Calls

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Nichols, Daniel, Singhania, Prajwal, Jekel, Charles, Bhatele, Abhinav, Menon, Harshitha
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Programming Languages Artificial Intelligence Distributed, Parallel, and Cluster Computing Performance Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Integrating Performance Tools in Model Reasoning for GPU Kernel Optimization
di: Nichols, Daniel, et al.
Pubblicazione: (2025)

Performance-Aligned LLMs for Generating Fast Code
di: Nichols, Daniel, et al.
Pubblicazione: (2024)

Understanding and Improving Communication Performance in Multi-node LLM Inference
di: Singhania, Prajwal, et al.
Pubblicazione: (2025)

HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages
di: Chaturvedi, Aman, et al.
Pubblicazione: (2024)

Leveraging AI for Productive and Trustworthy HPC Software: Challenges and Research Directions
di: Teranishi, Keita, et al.
Pubblicazione: (2025)

Optimizing OpenFaaS on Kubernetes: Comparative Analysis of Language Runtimes and Cluster Distributions
di: Ataie, Ehsan, et al.
Pubblicazione: (2026)

AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems
di: Wang, Zirui, et al.
Pubblicazione: (2026)

A 4D Hybrid Algorithm to Scale Parallel Training to Thousands of GPUs
di: Singh, Siddharth, et al.
Pubblicazione: (2023)

Taking GPU Programming Models to Task for Performance Portability
di: Davis, Joshua H., et al.
Pubblicazione: (2024)

LLMs as Packagers of HPC Software
di: Melone, Caetano, et al.
Pubblicazione: (2025)

High-level Stream Processing: A Complementary Analysis of Fault Recovery
di: Vogel, Adriano, et al.
Pubblicazione: (2024)

LibProf: A Python Profiler for Improving Cold Start Performance in Serverless Applications
di: Tariq, Syed Salauddin Mohammad, et al.
Pubblicazione: (2024)

When Should I Run My Application Benchmark?: Studying Cloud Performance Variability for the Case of Stream Processing Applications
di: Henning, Sören, et al.
Pubblicazione: (2025)

Where Should I Deploy My Contracts? A Practical Experience Report
di: Lazăr, Cătălina, et al.
Pubblicazione: (2025)

MPI Implementation Profiling for Better Application Performance
di: Shipley, Riley, et al.
Pubblicazione: (2024)

Should I Run My Cloud Benchmark on Black Friday?
di: Henning, Sören, et al.
Pubblicazione: (2025)

Automated Programmatic Performance Analysis of Parallel Programs
di: Cankur, Onur, et al.
Pubblicazione: (2024)

pyGinkgo: A Sparse Linear Algebra Operator Framework for Python
di: Tuteja, Keshvi, et al.
Pubblicazione: (2025)

Performant Automatic BLAS Offloading on Unified Memory Architecture with OpenMP First-Touch Style Data Movement
di: Li, Junjie
Pubblicazione: (2024)

HPC-Coder: Modeling Parallel Programs using Large Language Models
di: Nichols, Daniel, et al.
Pubblicazione: (2023)

KEET: Explaining Performance of GPU Kernels Using LLM Agents
di: Davis, Joshua H., et al.
Pubblicazione: (2026)

Optimized thread-block arrangement in a GPU implementation of a linear solver for atmospheric chemistry mechanisms
di: Ruiz, Christian Guzman, et al.
Pubblicazione: (2024)

AscendCraft: Automatic Ascend NPU Kernel Generation via DSL-Guided Transcompilation
di: Wen, Zhongzhen, et al.
Pubblicazione: (2026)

CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe
di: Saba, Tara, et al.
Pubblicazione: (2026)

Analytics of Longitudinal System Monitoring Data for Performance Prediction
di: Costello, Ian J., et al.
Pubblicazione: (2020)

Pipit: Scripting the analysis of parallel execution traces
di: Bhatele, Abhinav, et al.
Pubblicazione: (2023)

MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation
di: Wen, Zhongzhen, et al.
Pubblicazione: (2025)

A Delta-Aware Orchestration Framework for Scalable Multi-Agent Edge Computing
di: Singh, Samaresh Kumar, et al.
Pubblicazione: (2026)

Rethinking Performance Analysis for Configurable Software Systems: A Case Study from a Fitness Landscape Perspective
di: Huang, Mingyu, et al.
Pubblicazione: (2024)

Evaluating Asynchronous Semantics in Trace-Discovered Resilience Models: A Case Study on the OpenTelemetry Demo
di: Krasnovsky, Anatoly A.
Pubblicazione: (2025)

Emergence-as-Code for Self-Governing Reliable Systems
di: Krasnovsky, Anatoly A.
Pubblicazione: (2026)

Evaluating Fault Tolerance and Scalability in Distributed File Systems: A Case Study of GFS, HDFS, and MinIO
di: Malhotra, Shubham, et al.
Pubblicazione: (2025)

Adaptive Protein Design Protocols and Middleware
di: Alsaadi, Aymen, et al.
Pubblicazione: (2025)

Blink: CPU-Free LLM Inference by Delegating the Serving Stack to GPU and SmartNIC
di: Siavashi, Mohammad, et al.
Pubblicazione: (2026)

Record-Remix-Replay: Hierarchical GPU Kernel Optimization using Evolutionary Search
di: Nichols, Daniel, et al.
Pubblicazione: (2026)

CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming
di: TehraniJamsaz, Ali, et al.
Pubblicazione: (2024)

Black-Scholes Option Pricing on Intel CPUs and GPUs: Implementation on SYCL and Optimization Techniques
di: Panova, Elena, et al.
Pubblicazione: (2022)

Easy Acceleration with Distributed Arrays
di: Kepner, Jeremy, et al.
Pubblicazione: (2025)

Beating vDSP: A 138 GFLOPS Radix-8 Stockham FFT on Apple Silicon via Two-Tier Register-Threadgroup Memory Decomposition
di: Bergach, Mohamed Amine
Pubblicazione: (2026)

Do Large Language Models Understand Performance Optimization?
di: Cui, Bowen, et al.
Pubblicazione: (2025)