[Bugfix] Reject channelwise quantization (group_size <= 0) in ExllamaLinearKernel (#37331)

Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>

vllm/model_executor/kernels/linear/mixed_precision/exllama.py

@@ -59,6 +59,13 @@ class ExllamaLinearKernel(MPLinearKernel):
                 f"{cls.SUPPORTED_QUANT_TYPES}",
             )
 
+        if c.group_size <= 0:
+            return (
+                False,
+                f"Group size ({c.group_size}) must be positive, "
+                "Exllama does not support channelwise quantization",
+            )
+
         if c.full_weight_shape[0] % c.group_size != 0:
             return (
                 False,