Add missing assertion in NemotronH path (#15193)

Signed-off-by: Roi Koren <roik@nvidia.com>
2025-12-15 06:17:21 -08:00
parent 3518b33178
commit 9003a4369d
1 changed files with 3 additions and 0 deletions
@@ -1266,6 +1266,9 @@ class ServerArgs:
            )
            self.disable_radix_cache = True
        elif model_arch in ["NemotronHForCausalLM"]:
            assert (
                not self.enable_mamba_extra_buffer()
            ), f"mamba extra_buffer is not supported for {model_arch} model"
            model_config = self.get_model_config()
            if model_config.quantization in [
                "modelopt",