GLM-4.7-NVFP4

import sys
import os
import re

# Path to the vLLM model file
path = '/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/glm4_moe.py'

if os.path.exists(path):
    with open(path, 'r') as f:
        lines = f.readlines()
    
    target_str = 'param = params_dict[name]'
    new_lines = []
    patched = False
    
    for line in lines:
        # We look for the parameter loading line
        if target_str in line and 'k_scale' not in line:
            whitespace = re.match(r'^(\s*)', line).group(1)
            
            # Inject logic: If asking for k_scale/v_scale and it's missing, skip
            payload = f"{whitespace}if ('k_scale' in name or 'v_scale' in name) and name not in params_dict: continue\n"
            
            new_lines.append(payload)
            new_lines.append(line)
            patched = True
        else:
            new_lines.append(line)
            
    if patched:
        with open(path, 'w') as f:
            f.writelines(new_lines)
        print(f"Successfully patched {path}")
    else:
        print("File already patched or target not found.")