{"record":{"id":"da64bc2cebb36ecc","repo":"vllm-project/vllm","slug":"model-runner-v2-does-not-yet-support-join-u","errorCode":null,"errorMessage":"Model Runner V2 does not yet support: {', '.join(unsupported)}","messagePattern":"Model Runner V2 does not yet support: (.+?)","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"vllm/config/vllm.py","lineNumber":2486,"sourceCode":"            unsupported.append(\"custom logits processors\")\n\n        if model_config is not None and model_config.enable_prompt_embeds:\n            unsupported.append(\"prompt embeds\")\n\n        if self.cache_config.kv_sharing_fast_prefill:\n            # Will be added by https://github.com/vllm-project/vllm/pull/35045\n            unsupported.append(\"KV sharing fast prefill\")\n\n        return unsupported\n\n    def _validate_v2_model_runner(self) -> None:\n        \"\"\"Check for features not yet supported by the V2 model runner.\"\"\"\n        if not HAS_TRITON:\n            raise ValueError(\"Model Runner V2 requires Triton.\")\n\n        unsupported = self._get_v2_model_runner_unsupported_features()\n        if unsupported:\n            raise ValueError(\n                f\"Model Runner V2 does not yet support: {', '.join(unsupported)}\"\n            )\n\n    def validate_block_size(self) -> None:\n        \"\"\"Validate block_size against DCP and mamba constraints.\n\n        Called after Platform.update_block_size_for_backend() has\n        finalised block_size.\n        \"\"\"\n        block_size = self.cache_config.block_size\n\n        # DCP interleave-size compatibility\n        if self.parallel_config.decode_context_parallel_size > 1:\n            if self.parallel_config.dcp_kv_cache_interleave_size > 1 and (\n                self.parallel_config.cp_kv_cache_interleave_size\n                != self.parallel_config.dcp_kv_cache_interleave_size\n            ):\n                self.parallel_config.cp_kv_cache_interleave_size = (","sourceCodeStart":2468,"sourceCodeEnd":2504,"githubUrl":"https://github.com/vllm-project/vllm/blob/c794754062d49a8fdb63ab3c5215b488b865030c/vllm/config/vllm.py#L2468-L2504","documentation":"The V2 model runner has a curated list of not-yet-supported features (built by `_get_v2_model_runner_unsupported_features`, e.g. prompt embeds, KV sharing fast prefill, and others). If any of them is enabled, `_validate_v2_model_runner` raises with the comma-separated list so the user knows exactly what to disable.","triggerScenarios":"Running with the V2 model runner while any feature in the unsupported list is active — e.g. `enable_prompt_embeds=True` or `--kv-sharing-fast-prefill`.","commonSituations":"Opting into the newer V2 runner (or a default flip after upgrade) while a launch config still enables a feature the V1 runner supported; version upgrades that change the unsupported list.","solutions":["Disable each feature named in the error message (e.g. drop `--kv-sharing-fast-prefill`, unset prompt embeds).","Or switch back to the legacy runner with `VLLM_USE_V2_MODEL_RUNNER=0` until the feature is ported.","Check `_get_v2_model_runner_unsupported_features()` for your installed version to plan flag combinations."],"exampleFix":"# before (error: 'Model Runner V2 does not yet support: KV sharing fast prefill')\nVLLM_USE_V2_MODEL_RUNNER=1 vllm serve model --kv-sharing-fast-prefill\n\n# after\nVLLM_USE_V2_MODEL_RUNNER=1 vllm serve model","handlingStrategy":"validation","validationCode":"cfg = VllmConfig._get_v2_model_runner_unsupported_features  # introspect if accessible\n# practical guard: mirror the known list\nUNSUPPORTED = []\nif model_config.enable_prompt_embeds: UNSUPPORTED.append(\"prompt embeds\")\nif cache_config.kv_sharing_fast_prefill: UNSUPPORTED.append(\"KV sharing fast prefill\")\nif use_v2 and UNSUPPORTED: use_v2 = False","typeGuard":null,"tryCatchPattern":"try:\n    LLM(**args)\nexcept ValueError as e:\n    if \"Model Runner V2 does not yet support\" in str(e):\n        os.environ[\"VLLM_USE_V2_MODEL_RUNNER\"] = \"0\"\n    else:\n        raise","preventionTips":["Check the unsupported-features list after each vLLM upgrade","Keep V1 fallback switch documented when experimenting with V2 runner"],"tags":["model-runner","feature-support","startup-config"],"backgroundTag":null,"analyzedSha":"c794754062d49a8fdb63ab3c5215b488b865030c","analyzedAt":"2026-08-14T21:17:39.825Z","schemaVersion":2},"datasetVersion":"2026-08-15T22:17:37.221Z"}