Skip to content

AirLLM 2.8T LLM inference with single 4GB GPU

#174 fix mlx model load

Yu Li527effa73190
diff --git a/air_llm/setup.py b/air_llm/setup.py
index c730648..378272a 100644
--- a/air_llm/setup.py
+++ b/air_llm/setup.py
@@ -14,7 +14,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
setuptools.setup(
name="airllm",
- version="2.10.1",
+ version="2.10.2",
author="Gavin Li",
author_email="[email protected]",
description="AirLLM allows single 4GB GPU card to run 70B large language models without quantization, distillation or pruning. 8GB vmem to run 405B Llama3.1.",