update quantization readme

configs/quantization/hunyuan_i2v.json

@@ -6,7 +6,7 @@
     "cross_attn_1_type": "flash_attn3",
     "cross_attn_2_type": "flash_attn3",
     "seed": 0,
-    "dit_quantized_ckpt": "/mtc/gushiqiao/llmc_workspace/x2v_models/hunyuan/hunyuan_i2v_int8.pth",
+    "dit_quantized_ckpt": "/path/to/int8/model",
     "mm_config": {
         "mm_type": "W-int8-channel-sym-A-int8-channel-sym-dynamic-Vllm"
     }

configs/quantization/readme.md

-### TODO

scripts/quantization/readme.md

+# Model Quantization
+
+The config files for model quantization are available [here](https://github.com/ModelTC/lightx2v/tree/main/configs/quantization)
+
+By specifying --config_json to the specific config file, you can test quantization inference.
+
+Please refer our model quantization doc:
+
+[English doc: Model Quantization](https://lightx2v-en.readthedocs.io/en/latest/method_tutorials/quantization.html)
+
+[中文文档: 模型量化](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/method_tutorials/quantization.html)