Cover Image

Orion: Characterizing and Programming Apple's Neural Engine for LLM Training and Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Kumaresan, Ramchand
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Hardware Architecture Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Characterizing the Behavior of Training Mamba-based State Space Models on GPUs
by: Baruah, Trinayan, et al.
Published: (2025)

Non-Monotonic Latency in Apple MPS Decoding: KV Cache Interactions and Execution Regimes
by: Hendria, Willy Fitra
Published: (2026)

Scaling Laws for Floating Point Quantization Training
by: Sun, Xingwu, et al.
Published: (2025)

Understanding and Mitigating Errors of LLM-Generated RTL Code
by: Zhang, Jiazheng, et al.
Published: (2025)

KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training
by: Kumaresan, Ramchand
Published: (2026)

Ultra Memory-Efficient On-FPGA Training of Transformers via Tensor-Compressed Optimization
by: Tian, Jiayi, et al.
Published: (2025)

GRPO with State Mutations: Improving LLM-Based Hardware Test Plan Generation
by: Kochar, Dimple Vijay, et al.
Published: (2026)

Highly Optimized Kernels and Fine-Grained Codebooks for LLM Inference on Arm CPUs
by: Gope, Dibakar, et al.
Published: (2024)

Weight Block Sparsity: Training, Compilation, and AI Engine Accelerators
by: D'Alberto, Paolo, et al.
Published: (2024)

HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases
by: Zheng, Pingqing, et al.
Published: (2025)

Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View
by: Wu, Yanran, et al.
Published: (2025)

DeepRTL2: A Versatile Model for RTL-Related Tasks
by: Liu, Yi, et al.
Published: (2025)

From Loop Nests to Silicon: Mapping AI Workloads onto AMD NPUs with MLIR-AIR
by: Wang, Erwei, et al.
Published: (2025)

DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model
by: Liu, Yi, et al.
Published: (2025)

OPAL: Outlier-Preserved Microscaling Quantization Accelerator for Generative Large Language Models
by: Koo, Jahyun, et al.
Published: (2024)

Speculative Decoding for Verilog: Speed and Quality, All in One
by: Xu, Changran, et al.
Published: (2025)

Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications
by: Li, Yang, et al.
Published: (2024)

Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference
by: Chen, Hongzheng, et al.
Published: (2023)

PRISM: Breaking the O(n) Memory Wall in Long-Context LLM Inference via O(1) Photonic Block Selection
by: Park, Hyoseok, et al.
Published: (2026)

Allo: A Programming Model for Composable Accelerator Design
by: Chen, Hongzheng, et al.
Published: (2024)

LLM-Aided Compilation for Tensor Accelerators
by: Hong, Charles, et al.
Published: (2024)

Leveraging Stochastic Depth Training for Adaptive Inference
by: Korol, Guilherme, et al.
Published: (2025)

Dato: A Task-Based Programming Model for Dataflow Accelerators
by: Fang, Shihan, et al.
Published: (2025)

Streaming Tensor Programs: A Streaming Abstraction for Dynamic Parallelism
by: Sohn, Gina, et al.
Published: (2025)

Characterization and Mitigation of Training Instabilities in Microscaling Formats
by: Su, Huangyuan, et al.
Published: (2025)

Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference
by: Yubeaton, Patrick, et al.
Published: (2025)

The Graph's Apprentice: Teaching an LLM Low Level Knowledge for Circuit Quality Estimation
by: Moravej, Reza, et al.
Published: (2024)

RTL++: Graph-enhanced LLM for RTL Code Generation
by: Akyash, Mohammad, et al.
Published: (2025)

KLLM: Fast LLM Inference with K-Means Quantization
by: Wu, Xueying, et al.
Published: (2025)

QiMeng-CodeV-SVA: Training Specialized LLMs for Hardware Assertion Generation via RTL-Grounded Bidirectional Data Synthesis
by: Wu, Yutong, et al.
Published: (2026)

Decomposing Evolutionary Mixture-of-LoRA Architectures: The Routing Lever, the Lifecycle Penalty, and a Substrate-Conditional Boundary
by: Kumaresan, Ramchand
Published: (2026)

Performance Analysis of DNN Inference/Training with Convolution and non-Convolution Operations
by: Esmaeilzadeh, Hadi, et al.
Published: (2023)

ACAR: Adaptive Complexity Routing for Multi-Model Ensembles with Auditable Decision Traces
by: Kumaresan, Ramchand
Published: (2026)

Efficient and Mathematically Robust Operations for Certified Neural Networks Inference
by: Geyer, Fabien, et al.
Published: (2024)

VeriCache: Turning Lossy KV Cache into Lossless LLM Inference
by: Yao, Jiayi, et al.
Published: (2026)

InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference
by: Pan, Xiurui, et al.
Published: (2024)

DAISM: Digital Approximate In-SRAM Multiplier-based Accelerator for DNN Training and Inference
by: Sonnino, Lorenzo, et al.
Published: (2023)

P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats
by: Chen, Yuzong, et al.
Published: (2025)

LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits
by: Zhou, Zikai, et al.
Published: (2025)

PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices
by: Yan, Minghao, et al.
Published: (2023)