TeLLMe v2: An Efficient End-to-End Ternary LLM Prefill and Decode Accelerator with Table-Lookup Matmul on Edge FPGAs

• URL: http://arxiv.org/abs/2510.15926v2
• Date: Tue, 21 Oct 2025 17:20:02 GMT
• Title: TeLLMe v2: An Efficient End-to-End Ternary LLM Prefill and Decode Accelerator with Table-Lookup Matmul on Edge FPGAs
• Authors: Ye Qiao, Zhiheng Chen, Yifan Zhang, Yian Wang, Sitao Huang,
• Abstract summary: TeLLMe is a table-lookup-based ternary LLM accelerator for low-power edge FPGAs.<n>It supports both prefill and autoregressive decoding using 1.58-bit weights and 8-bit activations.<n>Under a 5W power budget, TeLLMe delivers up to 25tokens/s decoding throughput.
• Score: 9.646882213709814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the emergence of wearable devices and other embedded systems, deploying large language models (LLMs) on edge platforms has become an urgent need. However, this is challenging because of their high computational and memory demands. Although recent low-bit quantization methods (e.g., BitNet, DeepSeek) compress weights to as low as 1.58~bits with minimal accuracy loss, edge deployment is still constrained by limited on-chip resources, power budgets, and the often-neglected long latency of the prefill stage. We present \textbf{TeLLMe}, the first table-lookup-based ternary LLM accelerator for low-power edge FPGAs that fully supports both prefill and autoregressive decoding using 1.58-bit weights and 8-bit activations. TeLLMe incorporates several novel techniques, including (1) a table-lookup-based ternary matrix multiplication (TLMM) engine utilizing grouped activations and online precomputation for low resource utilization and high throughput; (2) a fine-grained analytic URAM-based weight buffer management scheme for efficient loading and compute engine access; (3) a streaming dataflow architecture that fuses floating-point element-wise operations with linear computations to hide latency; (4) a reversed-reordered prefill stage attention with fused attention operations for high memory efficiency; and (5) a resource-efficient specialized decoding stage attention. Under a 5~W power budget, TeLLMe delivers up to 25~tokens/s decoding throughput and 0.45--0.96~s time-to-first-token (TTFT) for 64--128 token prompts, marking a significant energy-efficiency advancement in LLM inference on edge FPGAs.

Related papers

• T-SAR: A Full-Stack Co-design for CPU-Only Ternary LLM Inference via In-Place SIMD ALU Reorganization [7.665240126732136]
  This paper presents T-SAR, the first framework to achieve scalable ternary LLM inference on CPUs.<n>T-SAR eliminates memory bottlenecks and maximizes data-level parallelism, delivering 5.6-24.5x and 1.1-86.2x improvements in GEMM latency and GEMV throughput.<n>T-SAR achieves up to 2.5-4.9x the energy efficiency of an NVIDIA Jetson AGX Orin, establishing a practical approach for efficient LLM inference on edge platforms.
  arXiv  Detail & Related papers  (2025-11-17T18:32:03Z)
• Spark Transformer: Reactivating Sparsity in FFN and Attention [53.221448818147024]
  We introduce Spark Transformer, a novel architecture that achieves a high level of activation sparsity in both FFN and the attention mechanism.<n>This sparsity translates to a 2.5x reduction in FLOPs, leading to decoding wall-time speedups of up to 1.79x on CPU and 1.40x on GPU.
  arXiv  Detail & Related papers  (2025-06-07T03:51:13Z)
• TeLLMe: An Energy-Efficient Ternary LLM Accelerator for Prefilling and Decoding on Edge FPGAs [5.889337608109388]
  TeLLMe is the first ternary LLM accelerator for low-power FPGAs.<n>It supports both prefill and autoregressive decoding using 1.58-bit weights and 8-bit activations.<n>Under a 7W power budget, TeLLMe delivers up to 9 tokens/s throughput over 1,024-token contexts.
  arXiv  Detail & Related papers  (2025-04-22T21:00:58Z)
• MEADOW: Memory-efficient Dataflow and Data Packing for Low Power Edge LLMs [5.88896081401217]
  We introduce MEADOW, a framework that significantly reduces the off-chip memory access for large language models.<n> MEADOW demonstrates 1.5x and 2.5x lower decode and prefill latency, respectively, compared to a GEMM-based LLM implementation.<n> MEADOW achieves an end-to-end latency improvement of over 40%, compared to prior LLM optimization works.
  arXiv  Detail & Related papers  (2025-02-14T23:50:37Z)
• Designing Efficient LLM Accelerators for Edge Devices [1.4128048241287314]
  Large Language Models (LLMs) can be deployed on resource-constrained edge devices to reduce reliance on network connections and provide more privacy. To address this issue, designing new and efficient edge accelerators for LLM inference is crucial. We propose SECDA-LLM, that utilizes the SECDA methodology to streamline the process of designing, integrating, and deploying efficient FPGA-based LLM accelerators.
  arXiv  Detail & Related papers  (2024-08-01T11:06:05Z)
• Fast Matrix Multiplications for Lookup Table-Quantized LLMs [58.11584672945781]
  FLUTE is a flexible lookup table engine for LUT-quantized LLMs.<n>At batch sizes 32 and quantization group size of 128, the FLUTE kernel can be 2-4x faster than existing GEMM kernels.
  arXiv  Detail & Related papers  (2024-07-15T17:55:42Z)
• SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs [3.302913401404089]
  Sliding window-based static sparse attention mitigates the problem by limiting the attention scope of the input tokens. We propose a dataflow-aware FPGA-based accelerator design, SWAT, that efficiently leverages the sparsity to achieve scalable performance for long input.
  arXiv  Detail & Related papers  (2024-05-27T10:25:08Z)
• HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference [68.59839755875252]
  HiRE comprises of two novel components: (i) a compression scheme to cheaply predict top-$k$ rows/columns with high recall, followed by full computation restricted to the predicted subset, and (ii) DA-TOP-$k$: an efficient multi-device approximate top-$k$ operator. We demonstrate that on a one billion parameter model, HiRE applied to both the softmax as well as feedforward layers, achieves almost matching pretraining and downstream accuracy, and speeds up inference latency by $1.47times$ on a single TPUv5e device.
  arXiv  Detail & Related papers  (2024-02-14T18:04:36Z)
• DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tables [49.965024476651706]
  DeepGEMM is a lookup table based approach for the execution of ultra low-precision convolutional neural networks on SIMD hardware. Our implementation outperforms corresponding 8-bit integer kernels by up to 1.74x on x86 platforms.
  arXiv  Detail & Related papers  (2023-04-18T15:13:10Z)
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation [81.76975488010213]
  Dense optical flow estimation plays a key role in many robotic vision tasks. Current networks often occupy large number of parameters and require heavy computation costs. Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations.
  arXiv  Detail & Related papers  (2021-03-08T03:09:37Z)
• EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference [82.1584439276834]
  Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. We present EdgeBERT, an in-depth algorithm- hardware co-design for latency-aware energy optimization for multi-task NLP.
  arXiv  Detail & Related papers  (2020-11-28T19:21:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.