Update README.md

README.md

@@ -23,6 +23,9 @@ python3 quantize_quark.py \
         --quant_scheme w_fp8_a_fp8 \
         --kv_cache_dtype fp8 \
         --num_calib_data 128 \
+        --model_export quark_safetensors \
+        --no_weight_matrix_merge \
+
 # If model size is too large for single GPU, please use multi GPU instead.
 python3 quantize_quark.py \ 
         --model_dir $MODEL_DIR \
@@ -30,6 +33,9 @@ python3 quantize_quark.py \
         --quant_scheme w_fp8_a_fp8 \
         --kv_cache_dtype fp8 \
         --num_calib_data 128 \
+        --model_export quark_safetensors \
+        --no_weight_matrix_merge \
+        --multi_gpu
 ```
 ## Deployment
 Quark has its own export format and allows FP8 quantized models to be efficiently deployed using the vLLM backend(vLLM-compatible).