LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
This addresses efficiency issues in long-context LLM inference for users needing faster generation, though it is incremental as it builds on existing pruning methods by adding dynamic selection.
The paper tackles the bottleneck in transformer-based LLM inference caused by computing KV caches for all prompt tokens during prefilling, introducing LazyLLM to dynamically prune tokens and accelerate generation without fine-tuning, achieving a 2.34x speedup in prefilling for the LLama 2 7B model in multi-document QA while maintaining accuracy.
The inference of transformer-based large language models consists of two sequential stages: 1) a prefilling stage to compute the KV cache of prompts and generate the first token, and 2) a decoding stage to generate subsequent tokens. For long prompts, the KV cache must be computed for all tokens during the prefilling stage, which can significantly increase the time needed to generate the first token. Consequently, the prefilling stage may become a bottleneck in the generation process. An open question remains whether all prompt tokens are essential for generating the first token. To answer this, we introduce a novel method, LazyLLM, that selectively computes the KV for tokens important for the next token prediction in both the prefilling and decoding stages. Contrary to static pruning approaches that prune the prompt at once, LazyLLM allows language models to dynamically select different subsets of tokens from the context in different generation steps, even though they might be pruned in previous steps. Extensive experiments on standard datasets across various tasks demonstrate that LazyLLM is a generic method that can be seamlessly integrated with existing language models to significantly accelerate the generation without fine-tuning. For instance, in the multi-document question-answering task, LazyLLM accelerates the prefilling stage of the LLama 2 7B model by 2.34x while maintaining accuracy.