KerColle: Unlocking Fine-Grained GPU Concurrency in Vision-Language-Action Models

arXiv:2609.22335 · cs.AR, cs.RO · Submitted 2026-09-16 · Read on arXiv

cs.AR, cs.RO

Submitted: 2026-09-16

Updated: 2026-09-16

Terminology

• Core — 51× in this paper · explained in 2 episodes
• Tensor Core — 21× in this paper
• VLA Models — 15× in this paper · explained in 3 episodes
• Action Chunking — 7× in this paper · explained in 1 episode
• Streaming Multiprocessor — 4× in this paper
• Foundation Model — 3× in this paper · explained in 3 episodes
• International Conference on Computer Design — 3× in this paper
• Trace — 3× in this paper · explained in 2 episodes
• Cooperative Thread Array — 2× in this paper
• Flow Matching — 2× in this paper · explained in 8 episodes
• High Performance Computer Architecture — 2× in this paper
• Transformer — 2× in this paper · explained in 2 episodes
• Vision-Language-Action (VLA) Models — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Action Decoder — 1× in this paper · explained in 1 episode
• Action Flow — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Diffusion Process — 1× in this paper · explained in 2 episodes
• Edge Devices — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Multi-Process Service — 1× in this paper
• Pure Vision Language Action — 1× in this paper
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• PaliGemma: A versatile 3B VLM for transfer
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• Real-Time Execution of Action Chunking Flow Policies
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
• RT-1: Robotics Transformer for Real-World Control at Scale
• GR-3 Technical Report
• Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning
• Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process
• cuDNN: Efficient Primitives for Deep Learning
• Open X-Embodiment: Robotic Learning Datasets and RT-X Models
• Kitsune: Enabling Dataflow Execution on GPUs
• GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data
• Characterizing Concurrency Mechanisms for NVIDIA GPUs under Deep Learning Workloads
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf
• AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models
• Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
• DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
• OpenVLA: An Open-Source Vision-Language-Action Model

Related papers

• WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization
• Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats
• PoisonCap: Efficient Hierarchical Temporal Safety for CHERI
• Provisioning to Runtime Optimization of a 100 MW-Scale AI Cluster
• Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy
• Optimizing Polynomial Multiplication and Fixed-Weight Sampling for HQC on ARM Cortex-M4