Model-Optimizer 投机解码实战指南:用 Medusa 与 EAGLE 将 LLM 推理延迟降至最低
人工智能大模型模型优化模型量化模型压缩 【免费下载链接】Model-Optimizer A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning mode…
2026/9/27 7:10:32