support moe offline quant (#5142)

2025-12-24 13:28:13 +08:00 · 2025-11-24 18:59:18 +08:00
parent 5ff93d4998
commit e150a418d4
5 changed files with 12 additions and 3 deletions
--- a/fastdeploy/config.py
+++ b/fastdeploy/config.py
@@ -180,6 +180,7 @@ class ModelConfig:
    ):
        self.model = ""
        self.is_quantized = False
+        self.is_moe_quantized = False
        self.max_model_len = 0
        self.dtype = "bfloat16"
        self.enable_logprob = False