Update README.md

README.md

@@ -43,6 +43,12 @@ It's fast on a 3070 Ti mobile.  Uses 5-6 GB of GPU RAM.
 * Removed bitsandbytes from requirements
 * Added pip installable branch based on winglian's PR
 * Added cuda backend quant attention and fused mlp from GPTQ_For_Llama.
+* Added lora patch for GPTQ_For_Llama triton backend.
+
+```
+from monkeypatch.gptq_for_llala_lora_monkey_patch import inject_lora_layers
+inject_lora_layers(model, lora_path, device, dtype)
+```
 
 # Requirements
 gptq-for-llama <br>