Large Language Models (LLMs) have achieved state-of-the-art performance across various language tasks but pose challenges for practical deployment due to their substantial memory requirements. Furthermore, the latest generative models suffer from high inference costs caused by the memory bandwidth bottleneck in the auto-regressive decoding process. To address these issues, we propose an efficient weight-only quantization method that reduces memory consumption and accelerates inference for LLMs. To ensure minimal quality degradation, we introduce a simple and effective heuristic approach that utilizes only the model weights of a pre-trained model. This approach is applicable to both Mixture-of-Experts (MoE) and dense models without requiring additional fine-tuning. To demonstrate the effectiveness of our proposed method, we first analyze the challenges and issues associated with LLM quantization. Subsequently, we present our heuristic approach, which adaptively finds the granularity of quantization, effectively addressing these problems. Furthermore, we implement highly efficient GPU GEMMs that perform on-the-fly matrix multiplication and dequantization, supporting the multiplication of fp16 or bf16 activations with int8 or int4 weights. We evaluate our approach on large-scale open source models such as OPT-175B and internal MoE models, showcasing minimal accuracy loss while achieving up to 3.65 times higher throughput on the same number of GPUs.

为了解决大型语言模型在实际应用中的内存需求和推断成本的问题，我们提出了一种高效的仅权重量化方法，通过减少内存消耗和加速推断来实现。我们引入了一种简单而有效的启发式方法，仅利用预训练模型的模型权重来确保最小质量降低。该方法适用于混合专家模型和密集模型，并且无需额外的微调。通过分析量化大型语言模型的挑战和问题，并采用自适应的量化粒度进行解决，我们展示了我们提出的方法的有效性。此外，我们实现了高效的GPU矩阵乘法和解量化算法，支持fp16或bf16激活与int8或int4权重的乘法。我们在OPT-175B和内部混合专家模型等大规模开源模型上评估了我们的方法，展示了最小的准确性损失，并在相同数量的GPU上实现了高达3.65倍的吞吐量。

FineQuant: 低精度量化后全连接网络权重细粒度优化