Communication Compression for Tensor Parallel LLM Inference

• URL: http://arxiv.org/abs/2411.09510v2
• Date: Fri, 15 Nov 2024 10:47:37 GMT
• Title: Communication Compression for Tensor Parallel LLM Inference
• Authors: Jan Hansen-Palmus, Michael Truong Le, Oliver Hausdörfer, Alok Verma,
• Abstract summary: Large Language Models (LLMs) have pushed the frontier of artificial intelligence but are comprised of hundreds of billions of parameters and operations. For faster inference latency, LLMs are deployed on multiple hardware accelerators through various Model Parallelism strategies. Our paper looks into the details on one such strategy - Parallel - and proposes to reduce latency by compressing inter-accelerator communication.
• Score: 1.199955563466263
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have pushed the frontier of artificial intelligence but are comprised of hundreds of billions of parameters and operations. For faster inference latency, LLMs are deployed on multiple hardware accelerators through various Model Parallelism strategies. Our paper looks into the details on one such strategy - Tensor Parallel - and proposes to reduce latency by compressing inter-accelerator communication. We leverage fine grained quantization techniques to compress selected activations by 3.5 - 4.5x. Our proposed method leads up to 2x reduction of time-to-first-token (TTFT) with negligible model performance degradation.

Related papers

• Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computing [8.705453442427585]
  Large language models (LLMs) have achieved near-human performance across diverse reasoning tasks.<n>Their deployment on resource-constrained Internet-of-Things (IoT) devices remains impractical due to massive parameter footprints and memory-intensive autoregressive decoding.<n>This work introduces the first autoregressive-aware split computing framework designed explicitly for LLM deployment on edge devices.
  arXiv  Detail & Related papers  (2025-11-06T02:55:07Z)
• PT$^2$-LLM: Post-Training Ternarization for Large Language Models [52.4629647715623]
  Large Language Models (LLMs) have shown impressive capabilities across diverse tasks, but their large memory and compute demands hinder deployment.<n>We propose PT$2$-LLM, a post-training ternarization framework tailored for LLMs.<n>At its core is an Asymmetric Ternary Quantizer equipped with a two-stage refinement pipeline.
  arXiv  Detail & Related papers  (2025-09-27T03:01:48Z)
• CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems [62.24576366776727]
  We propose a latency-aware scheduling framework to minimize total inference latency.<n>We show that the proposed method significantly reduces cold-start latency compared to baseline strategies.
  arXiv  Detail & Related papers  (2025-08-15T07:49:22Z)
• LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit [29.877232989285833]
  Large Vision-Language Models (VLMs) exhibit impressive multi-modal capabilities but suffer from prohibitive computational and memory demands.<n>Current approaches do not decompose techniques into comparable modules, hindering fair evaluation across spatial and temporal redundancy.<n>We introduce LLMC+, a comprehensive VLM compression benchmark with a versatile, plug-and-play toolkit.
  arXiv  Detail & Related papers  (2025-08-13T17:54:49Z)
• Optimal Scheduling Algorithms for LLM Inference: Theory and Practice [6.043830060363904]
  This paper develops a theoretical framework that models routing and scheduling in Large Language Model inference systems.<n>We identify two key design principles-optimal tiling and dynamic resource allocation-that are essential for achieving high throughput.<n>We show that the Resource-Aware Dynamic (RAD) scheduler achieves throughput optimality under mild conditions.
  arXiv  Detail & Related papers  (2025-08-01T18:12:21Z)
• Communication-Efficient Multi-Device Inference Acceleration for Transformer Models [19.938589623698338]
  Transformer models power many AI applications but suffer from high inference latency, limiting their use in real-time settings.<n>We propose ASTRA, a communication-efficient framework that accelerates Transformer inference through a novel integration of sequence parallelism and a Mixed-Precision Attention mechanism designed to minimize inter-device communication.<n>ASTRA achieves up to 2.64X speedups over single-device inference and up to 15.25X speedups over state-of-the-art multi-device inferences, while operating under bandwidths as low as 10 Mbps.
  arXiv  Detail & Related papers  (2025-05-25T22:16:59Z)
• Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference [14.805702987440512]
  We introduce Flash Communication, a novel low-bit compression technique designed to alleviate the tensor-parallelism communication bottleneck during inference. Our method substantially boosts intra-node communication speed by more than 3x and reduces the time-to-first-token by 2x, with nearly no sacrifice in model accuracy.
  arXiv  Detail & Related papers  (2024-12-06T11:29:32Z)
• EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation [84.70637613266835]
  EoRA is a fine-tuning-free method that augments compressed Large Language Models with low-rank matrices.<n>EoRA consistently outperforms prior training-free low rank methods in recovering the accuracy of compressed LLMs.
  arXiv  Detail & Related papers  (2024-10-28T17:59:03Z)
• BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression [91.23933111083389]
  BRIEF (Bridging Retrieval and Inference through Evidence Fusion) is a lightweight approach that performs query-aware multi-hop reasoning. Based on our synthetic data built entirely by open-source models, BRIEF generates more concise summaries.
  arXiv  Detail & Related papers  (2024-10-20T04:24:16Z)
• Mnemosyne: Parallelization Strategies for Efficiently Serving Multi-Million Context Length LLM Inference Requests Without Approximations [8.881243419237608]
  We propose three key innovations for efficient interactive long context inference. These are adaptive chunking to reduce prefill overheads in mixed, Sequence Pipeline Parallelism (SPP) and Cache Parallelism (KVP) These contributions are combined into a 3D strategy, enabling Mnemosyne to scale interactive inference to context lengths at least up to 10 million tokens with high throughput enabled with parallelism.
  arXiv  Detail & Related papers  (2024-09-25T18:21:05Z)
• ISO: Overlap of Computation and Communication within Seqenence For LLM Inference [8.616769297336708]
  This paper introduces a novel strategy for computation-communication overlap that operates at the sequence level. Experimental evaluations conducted using 30b/70b models have demonstrated significant improvements in efficiency.
  arXiv  Detail & Related papers  (2024-09-04T05:22:17Z)
• MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models [58.3342517278868]
  This paper describes the design of Mixed-precision AutoRegressive LINear kernels. It shows that batchsizes up to 16-32 can be supported with close to maximum ($4times$) quantization speedup. MarLIN accomplishes this via a combination of techniques, such as asynchronous memory access, complex task scheduling and pipelining.
  arXiv  Detail & Related papers  (2024-08-21T16:10:41Z)
• ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization [13.622268474310918]
  ShiftAddLLM is an efficient multiplication-free model for large language models. It achieves perplexity improvements of 5.6 and 22.7 points at comparable or lower latency. Experiments on five LLM families and eight tasks consistently validate the effectiveness of ShiftAddLLM.
  arXiv  Detail & Related papers  (2024-06-10T02:47:55Z)
• 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)
• Extreme Compression of Large Language Models via Additive Quantization [59.3122859349777]
  Our algorithm, called AQLM, generalizes the classic Additive Quantization (AQ) approach for information retrieval. We provide fast GPU and CPU implementations of AQLM for token generation, which enable us to match or outperform optimized FP16 implementations for speed.
  arXiv  Detail & Related papers  (2024-01-11T18:54:44Z)
• LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models [22.06402870816756]
  Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. This paper presents LLMLingua, a coarse-to-fine prompt compression method that involves a budget controller to maintain semantic integrity. We show that the proposed approach yields state-of-the-art performance and allows for up to 20x compression with little performance loss.
  arXiv  Detail & Related papers  (2023-10-09T14:10:21Z)
• Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt [96.24800696597707]
  We introduce a new perspective to optimize this trade-off by prompting compressed models. We propose a soft prompt learning method where we expose the compressed model to the prompt learning process. Our experimental analysis suggests our soft prompt strategy greatly improves the performance of the 8x compressed LLaMA-7B model.
  arXiv  Detail & Related papers  (2023-05-17T20:45:13Z)
• Parameter-efficient Tuning of Large-scale Multimodal Foundation Model [68.24510810095802]
  We propose A graceful prompt framework for cross-modal transfer (Aurora) to overcome these challenges. Considering the redundancy in existing architectures, we first utilize the mode approximation to generate 0.1M trainable parameters to implement the multimodal prompt tuning. A thorough evaluation on six cross-modal benchmarks shows that it not only outperforms the state-of-the-art but even outperforms the full fine-tuning approach.
  arXiv  Detail & Related papers  (2023-05-15T06:40:56Z)
• Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees [33.38465345409054]
  We show that AC-SGD can be combined with state-of-the-art gradient compression algorithms to enable "end-to-end compression" AC-SGD provides up to 4.3X end-to-end speed-up in slower networks, without sacrificing model quality.
  arXiv  Detail & Related papers  (2022-06-02T20:49:12Z)

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.