The rapid growth of model parameters presents a significant challenge when deploying large generative models on GPU. Existing LLM runtime memory management solutions tend to maximize batch size to saturate GPU device utilization. Nevertheless, this practice leads to situations where the KV Cache of certain sequences cannot be accommodated on GPUs with limited memory capacity during the model inference, requiring temporary eviction from GPU memory (referred to as KV Cache spillover). However, without careful consideration of the LLM inference's runtime pattern, current LLM inference memory management solutions face issues like one-size-fits-all spillover handling approach for different platforms, under-utilization of GPU in prefill stage, and suboptimal sequence selection due to direct employment of swap or recomputation. In this paper, we introduce FuseSpill, a holistic KV Cache management solution designed to boost LLM inference on memory-constrained GPU by efficiently handling KV Cache spillover. Specifically, FuseSpill consists of a spillover cost model that analyzes the system cost of spillover handling techniques quantitatively, a KV cache swap orchestrator to further refine the basic swap technique to sophisticated disaggregate KV Cache across heterogeneous devices for decoding iterations, a multi-executor scheduler to effectively coordinate task executors across devices, and a response length predictor to exploit the length-aware sequence selection strategy when KV Cache spillover occurs. The experimental results demonstrate that our implementation outperforms existing solutions, delivering a 20% to 40% increase in throughput while simultaneously reducing the inference latency of the spillover sequences.

As the model size continuously increases, pipeline parallelism shows great promise in throughput-oriented LLM inference due to its low demand on communications. However, imbalanced pipeline workloads and complex data dependencies in the prefill and decode phases result in massive pipeline bubbles and further severe performance reduction.

Transformer models have emerged as a leading approach in the field of natural language processing (NLP) and are increasingly being deployed in production environments. Graphic processing units (GPUs) have become a popular choice for the transformer deployment and often rely on the batch processing technique to ensure high hardware performance. Nonetheless, the current practice for transformer inference encounters computational and memory redundancy due to the heavy-tailed distribution of sequence lengths in NLP scenarios, resulting in low practical performance. In this article, we propose a unified solution for improving both computation and memory efficiency of the real-world transformer inference on GPUs. The solution eliminates the redundant computation and memory footprint across a transformer model. At first, a GPU-oriented computation approach is proposed to process the self-attention module in a fine-grained manner, eliminating its redundant computation. Next, the multi-layer perceptron module continues to use the word-accumulation approach to eliminate its redundant computation. Then, to better unify the fine-grained approach and the word-accumulation approach, it organizes the data layout of the self-attention module in block granularity. Since aforementioned approaches make the required memory size largely reduce and constantly fluctuate, we propose the chunk-based approach to enable a better balance between memory footprint and allocation/free efficiency. Our experimental results show that our unified solution achieves a decrease of average latency by 28% on the entire transformer model, 63.8% on the self-attention module, and reduces memory footprint of intermediate results by 7.8×, compared with prevailing frameworks.