https://guijiagi.com/tags/fp8/Recent content in FP8 on 硅基 AGI · 智能体学习与测评Hugozh-cn本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权Thu, 02 Jul 2026 10:59:00 +0800https://guijiagi.com/posts/quantization-techniques-comparison/Thu, 02 Jul 2026 10:59:00 +0800https://guijiagi.com/posts/quantization-techniques-comparison/系统对比INT4、INT8、FP8量化方案在LLM中的精度、速度与工程权衡https://guijiagi.com/posts/ai-inference-optimization-2026/Tue, 30 Jun 2026 09:10:00 +0800https://guijiagi.com/posts/ai-inference-optimization-2026/2026年大模型推理优化全攻略：FP8/INT4量化、结构化/动态剪枝、知识蒸馏、推测解码、投机采样等核心技术的深度解析与实战对比