{"record":{"id":"ed345fc183049c1a","repo":"vllm-project/vllm","slug":"use-replayssm-requires-mamba-backend-triton","errorCode":null,"errorMessage":"--use-replayssm requires --mamba-backend triton","messagePattern":"--use-replayssm requires --mamba-backend triton","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"vllm/config/vllm.py","lineNumber":2578,"sourceCode":"        if not self.cache_config.use_replayssm:\n            return self\n        # ReplaySSM adds a 3-tensor ring to the mamba state; only models that\n        # opt in (supports_replayssm) build a consistent shape on both the layer\n        # and config paths. Reject others so the mamba page size cannot desync.\n        if self.model_config is not None and not self.model_config.supports_replayssm:\n            raise ValueError(\n                \"--use-replayssm is only supported for Nemotron-H models \"\n                f\"(got architecture {self.model_config.architecture!r})\"\n            )\n        if self.cache_config.mamba_cache_mode == \"all\":\n            raise ValueError(\n                \"--use-replayssm supports prefix caching only in align mode; \"\n                \"pass --mamba-cache-mode align\"\n            )\n        if self.num_speculative_tokens > 0:\n            raise ValueError(\"--use-replayssm does not support speculative decoding\")\n        if self.mamba_config.backend != MambaBackendEnum.TRITON:\n            raise ValueError(\"--use-replayssm requires --mamba-backend triton\")\n        if (\n            self.kv_transfer_config is not None\n            and self.kv_transfer_config.is_kv_transfer_instance\n        ):\n            raise ValueError(\n                \"--use-replayssm is incompatible with KV connectors \"\n                \"(P/D disaggregation, KV cache offload)\"\n            )\n        return self\n\n\n_current_vllm_config: VllmConfig | None = None\n_current_prefix: str | None = None\n\n\n@contextmanager\ndef set_current_vllm_config(\n    vllm_config: VllmConfig, check_compile=False, prefix: str | None = None","sourceCodeStart":2560,"sourceCodeEnd":2596,"githubUrl":"https://github.com/vllm-project/vllm/blob/c794754062d49a8fdb63ab3c5215b488b865030c/vllm/config/vllm.py#L2560-L2596","documentation":"Raised by VllmConfig.validate_mamba_cached_kernel when ReplaySSM (--use-replayssm) is enabled but the mamba backend is not the Triton one (mamba_config.backend != MambaBackendEnum.TRITON). The ReplaySSM replay path is only implemented against the Triton mamba kernels, so other backends (e.g. the CUDA/FLA variants) are rejected.","triggerScenarios":"Launching with --use-replayssm while --mamba-backend is set to a non-triton value, or defaults to one in the current build.","commonSituations":"Reusing a config tuned for the CUDA mamba backend and adding --use-replayssm on top; a platform where the default mamba backend is not Triton.","solutions":["Pass --mamba-backend triton together with --use-replayssm.","Check for typos in the backend name; the value must map to MambaBackendEnum.TRITON."],"exampleFix":"# before\nvllm serve NVIDIA/Nemotron-H-8B-V1 --use-replayssm --mamba-backend cuda\n# after\nvllm serve NVIDIA/Nemotron-H-8B-V1 --use-replayssm --mamba-backend triton","handlingStrategy":"validation","validationCode":"if cfg.cache_config.use_replayssm and str(cfg.mamba_config.backend).lower() != \"triton\":\n    raise SystemExit(\"--use-replayssm requires --mamba-backend triton\")","typeGuard":"def replayssm_backend_ok(cfg) -> bool:\n    from vllm.config.mamba import MambaBackendEnum\n    return (not cfg.cache_config.use_replayssm\n            or cfg.mamba_config.backend == MambaBackendEnum.TRITON)","tryCatchPattern":"try:\n    cfg = VllmConfig.from_cli(args)\nexcept ValueError as e:\n    if \"mamba-backend\" in str(e):\n        args[\"mamba_backend\"] = \"triton\"; revalidate(args)\n    raise","preventionTips":["Treat --mamba-backend triton as part of the replayssm preset; always set them together.","Pin launch scripts to known-good flag bundles validated against the deployed vLLM version."],"tags":["vllm","config","mamba","triton","replayssm"],"backgroundTag":null,"analyzedSha":"c794754062d49a8fdb63ab3c5215b488b865030c","analyzedAt":"2026-08-14T21:17:39.825Z","schemaVersion":2},"datasetVersion":"2026-08-15T22:17:37.221Z"}