MOM: Memory-Efficient Offloaded Mini-Sequence Inference for Long Context Language Models

• URL: http://arxiv.org/abs/2504.12526v1
• Date: Wed, 16 Apr 2025 23:15:09 GMT
• Title: MOM: Memory-Efficient Offloaded Mini-Sequence Inference for Long Context Language Models
• Authors: Junyang Zhang, Tianyi Zhu, Cheng Luo, Anima Anandkumar,
• Abstract summary: We propose Memory-efficient Offloaded Mini-sequence Inference (MOM)<n>MOM partitions critical layers into smaller "mini-sequences" and integrates seamlessly with KV cache offloading.<n>On Meta-Llama-3.2-8B, MOM extends the maximum context length from 155k to 455k tokens on a single A100 80GB GPU.
• Score: 72.61076288351201
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-context language models exhibit impressive performance but remain challenging to deploy due to high GPU memory demands during inference. We propose Memory-efficient Offloaded Mini-sequence Inference (MOM), a method that partitions critical layers into smaller "mini-sequences" and integrates seamlessly with KV cache offloading. Experiments on various Llama, Qwen, and Mistral models demonstrate that MOM reduces peak memory usage by over 50\% on average. On Meta-Llama-3.2-8B, MOM extends the maximum context length from 155k to 455k tokens on a single A100 80GB GPU, while keeping outputs identical and not compromising accuracy. MOM also maintains highly competitive throughput due to minimal computational overhead and efficient last-layer processing. Compared to traditional chunked prefill methods, MOM achieves a 35\% greater context length extension. More importantly, our method drastically reduces prefill memory consumption, eliminating it as the longstanding dominant memory bottleneck during inference. This breakthrough fundamentally changes research priorities, redirecting future efforts from prefill-stage optimizations to improving decode-stage residual KV cache efficiency.

Related papers

• MoM: Linear Sequence Modeling with Mixture-of-Memories [9.665802842933209]
  We introduce a novel architecture called Mixture-of-Memories (MoM)<n>MoM utilizes multiple independent memory states, with a router network directing input tokens to specific memory states.<n>MoM performs exceptionally well on recall-intensive tasks, surpassing existing linear sequence modeling techniques.
  arXiv  Detail & Related papers  (2025-02-19T12:53:55Z)
• CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs [45.77132019859689]
  CalibQuant is a visual quantization strategy that drastically reduces both memory and computational overhead. We achieve a 10x throughput increase on InternVL models.
  arXiv  Detail & Related papers  (2025-02-15T05:08:01Z)
• InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU [48.105361428245736]
  We introduce InfiniteHiP, an inference framework for large language models (LLMs)<n>We dynamically eliminate irrelevant context tokens through a modular hierarchical token pruning algorithm.<n>Our framework achieves an 18.95x speedup in attention decoding for a 1 million token context without requiring additional training.
  arXiv  Detail & Related papers  (2025-02-13T02:52:01Z)
• ThinK: Thinner Key Cache by Query-Driven Pruning [63.13363917871414]
  Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications.<n>This paper focuses on the long-context scenario, addressing the inefficiencies in KV cache memory consumption during inference.<n>We propose ThinK, a novel query-dependent KV cache pruning method designed to minimize attention weight loss while selectively pruning the least significant channels.
  arXiv  Detail & Related papers  (2024-07-30T17:59:08Z)
• vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving [53.972175896814505]
  Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests.
  arXiv  Detail & Related papers  (2024-07-22T14:37:58Z)
• Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training [78.93900796545523]
  Mini-Sequence Transformer (MsT) is a methodology for highly efficient and accurate LLM training with extremely long sequences. MsT partitions input sequences and iteratively processes mini-sequences to reduce intermediate memory usage. integrated with the huggingface library, MsT successfully extends the maximum context length of Qwen, Mistral, and Gemma-2 by 12-24x.
  arXiv  Detail & Related papers  (2024-07-22T01:52:30Z)
• MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training [24.066283519769968]
  Large Language Models (LLMs) have been trained using extended context lengths to foster more creative applications.<n>We propose MEMO, a novel framework for fine-grained activation memory management.<n>MeMO achieves an average of 1.97x and 1.80x MFU compared to Megatron-LM and DeepSpeed.
  arXiv  Detail & Related papers  (2024-07-16T18:59:49Z)
• Training-Free Exponential Context Extension via Cascading KV Cache [49.608367376911694]
  We introduce a novel mechanism that leverages cascading sub-cache buffers to selectively retain the most relevant tokens. Our method reduces prefill stage latency by a factor of 6.8 when compared to flash attention on 1M tokens.
  arXiv  Detail & Related papers  (2024-06-24T03:59:17Z)
• Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs [61.40047491337793]
  We present Hierarchical cOntext MERging (HOMER), a new training-free scheme designed to overcome the limitations of large language models. HomeR uses a divide-and-conquer algorithm, dividing long inputs into manageable chunks. A token reduction technique precedes each merging, ensuring memory usage efficiency.
  arXiv  Detail & Related papers  (2024-04-16T06:34:08Z)

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.