Turn off 2:4 sparse compression until supported in vllm

Author: rahul-tuli

examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py

@@ -116,5 +116,7 @@ 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, save_compressed=args.fp8, disable_sparse_compression=True
+)
 tokenizer.save_pretrained(save_dir)