PackMamba: Efficient Processing of Variable-Length Sequences in Mamba training
원문 초록
With the evolution of large language models, traditional Transformer models become computationally demanding for lengthy sequences due to the quadratic growth in computation with respect to the sequence length. Mamba, emerging as a groundbreaking architecture in the field of generative AI, demonstrates remarkable proficiency in handling elongated sequences with reduced computational and memory complexity. Nevertheless, the existing training framework of Mamba presents inefficiency with variable-length sequence inputs. Either single-sequence training results in low GPU utilization, or batched processing of variable-length sequences to a maximum length incurs considerable memory and computational overhead. To address this problem, we analyze the performance of bottleneck operators in Mamba under diverse tensor shapes and proposed PackMamba, a high-throughput Mamba that efficiently handles variable-length sequences. Diving deep into state-space models (SSMs), we modify the parallel operators to avoid passing information between individual sequences while maintaining high performance. Experimental results on an NVIDIA A100 GPU demonstrate throughput exceeding the baseline single-sequence processing scheme: 3.06x speedup on the 1.4B model and 2.62x on the 2.8B model.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MT-PCR: A Hybrid Mamba-Transformer with Spatial Serialization for Hierarchical Point Cloud Registration
FastMamba: A High-Speed and Efficient Mamba Accelerator on FPGA with Accurate Quantization
MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection
Sparsified State-Space Models are Efficient Highway Networks
Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings
JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.