save commpressed by defualt

vllm-project · Feb 20, 2025 · a4c99a5 · a4c99a5
1 parent ff007b6
commit a4c99a5
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py b/examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py
@@ -116,5 +116,5 @@ def get_recipe(fp8_enabled):
 print("==========================================\n")
 
 # Save compressed model and tokenizer
-model.save_pretrained(save_dir, save_compressed=args.fp8)
+model.save_pretrained(save_dir)
 tokenizer.save_pretrained(save_dir)