vllm-project/vllm · error · ValueError

Video pruning method '{pruning_spec[0]}' is not supported by

Error message

Video pruning method '{pruning_spec[0]}' is not supported by {self._model_info.architecture} (supported methods: {supported_pruning}).

What it means

Error "Video pruning method '{pruning_spec[0]}' is not supported by {self._model_info.architecture} (supported methods: {supported_pruning})." thrown in vllm-project/vllm.

Source

Thrown at vllm/config/model.py:811

                mm_device_do_normalize=self._resolve_mm_device_do_normalize(
                    mm_device_do_normalize
                ),
            )

            mm_config_kwargs = {
                k: v for k, v in mm_config_kwargs.items() if v is not None
            }

            self.multimodal_config = MultiModalConfig(**mm_config_kwargs)  # type: ignore[arg-type]

            pruning_spec = self.multimodal_config.get_video_pruning_spec()
            supported_pruning = self._model_info.supported_video_pruning_methods
            if (
                pruning_spec is not None
                and supported_pruning
                and pruning_spec[0] not in supported_pruning
            ):
                raise ValueError(
                    f"Video pruning method '{pruning_spec[0]}' is not "
                    f"supported by {self._model_info.architecture} "
                    f"(supported methods: {supported_pruning})."
                )

            if (
                self.renderer_num_workers > 1
                and self.multimodal_config.mm_processor_cache_gb > 0
                and self.runner_type == "pooling"
            ):
                raise ValueError(
                    "Cannot use --renderer-num-workers > 1 with the "
                    "multimodal processor cache enabled for pooling models. "
                    "Pooling preprocessing runs on the renderer workers, and "
                    "the cache is not thread-safe. Please set "
                    "--renderer-num-workers 1 (the default), or "
                    "disable the cache with --mm-processor-cache-gb 0."
                )

View on GitHub (pinned to c794754062)

Solutions

1. Choose one of the supported video pruning methods listed in the error for this model architecture.

When it happens

Trigger: Raised at vllm/config/model.py:811 when validation fails: Video pruning method is not supported by this model architecture. Typically triggered by an incompatible or incomplete vLLM configuration, an unsupported platform/backend combination, or a runtime resource/dependency that is missing.

Common situations: Commonly encountered at vllm/config/model.py:811 during vLLM startup/config validation or runtime setup when: (1) conflicting CLI flags or config fields are combined, (2) the current platform (CUDA/ROCm/CPU/XPU) or installed optional packages do not support the requested feature, or (3) a required value is absent or out of range. Resolve by correcting the configuration as described in the message, or by selecting a supported alternative.

AI-assisted analysis of vllm-project/vllm@c794754062 (2026-08-14). Data as JSON: /api/errors/657eb79fd46b056e. Report an issue: GitHub.