add logo

air_llm/README.md

@@ -1,4 +1,4 @@
-AirLLM optimizes inference memory usage, allowing 70B large language models to run inference on a single 4GB GPU card. No quantization, distillation, pruning or other model compression techniques that would result in degraded model performance are needed.
+![airllm_logo](https://github.com/lyogavin/Anima/blob/main/assets/airllm_logo_sm.png?v=2&raw=true)AirLLM optimizes inference memory usage, allowing 70B large language models to run inference on a single 4GB GPU card. No quantization, distillation, pruning or other model compression techniques that would result in degraded model performance are needed.
 
 AirLLM优化inference内存，4GB单卡GPU可以运行70B大语言模型推理。不需要任何损失模型性能的量化和蒸馏，剪枝等模型压缩。