Support fakequant serve with latest vllm and generalize calibration logic

Signed-off-by: weimingc <[email protected]>

Author: RalphMao

.pre-commit-config.yaml

@@ -32,7 +32,7 @@ repos:
       - id: mypy
 
   - repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v21.1.0
+    rev: v9.0.0
     hooks:
       - id: clang-format
         types_or: [c++, c, c#, cuda, java, javascript, objective-c, proto] # no json!