[Bugfix] fix w8a8_int8 load issue (#8308)

Co-authored-by: ronnie_zheng <zl19940307@163.com>
2025-08-01 08:30:16 +08:00
parent fe5086fd8b
commit 99795d61e6
2 changed files with 6 additions and 1 deletions
--- a/python/sglang/srt/model_loader/weight_utils.py
+++ b/python/sglang/srt/model_loader/weight_utils.py
@@ -229,6 +229,8 @@ def get_quant_config(
                    f"Unsupported quantization config"
                    f" found for {model_config.quantization} in {f}."
                )
+        elif model_config.quantization == "w8a8_int8":
+            config["packed_modules_mapping"] = packed_modules_mapping

    return quant_cls.from_config(config)