§ -`ƒi×ãóN—ddlmZddlmZmZddlmZmZGd„de¦«ZdS)é)ÚCallable)ÚAnyÚProtocol)Ú CUDAGraphModeÚ VllmConfigc óR—eZdZdZdedefdedededdf d „Zd ededefd „Z dS) ÚAbstractStaticGraphWrapperzu StaticGraphWrapper interface that allows platforms to wrap a callable to be captured as a static graph. Úrunnable.Ú vllm_configÚ runtime_modeÚkwargsÚreturnNc ó—t‚)a¹ Initializes the StaticGraphWrapper class with graph capturing and execution-related configurations. Args: runnable (Callable): The callable to be wrapped and captured. vllm_config (VllmConfig): Global configuration for vLLM. runtime_mode (CUDAGraphMode): The style of the static graph runtime. See CUDAGraphMode in vllm/config.py. Note that only the subset enum `NONE`, `PIECEWISE` and `FULL` are used as concrete runtime mode for cudagraph dispatching. Keyword Args: kwargs: Additional keyword arguments for platform-specific configurations. ©ÚNotImplementedError)Úselfr r r r s úv/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/vllm/compilation/base_static_graph.pyÚ__init__z#AbstractStaticGraphWrapper.__init__s €õ,"Ð!óÚargscó—t‚)a; Executes the wrapped callable. If the current runtime mode in the ForwardContext matches the runtime mode of this instance, it replays the CUDAGraph or captures it using the callable if it hasn't been captured yet. Otherwise, it calls the original callable directly. Args: *args: Variable length input arguments to be passed into the callable. **kwargs: Keyword arguments to be passed into the callable. Returns: Any: Output of the executed callable. r)rrr s rÚ__call__z#AbstractStaticGraphWrapper.__call__(s €õ""Ð!r) Ú__name__Ú __module__Ú __qualname__Ú__doc__rrrrrr©rrr r s”€€€€€ððð "à˜3 ˜8Ô$ð"ð ð"ð$ð "ð ð "ð ð "ð"ð"ð"ð0"˜cð"¨Sð"°Sð"ð"ð"ð"ð"ð"rr N) Úcollections.abcrÚtypingrrÚ vllm.configrrr rrrúr!s}ðð%Ð$Ð$Ð$Ð$Ð$Ø Ð Ð Ð Ð Ð Ð Ð à1Ð1Ð1Ð1Ð1Ð1Ð1Ð1ð/"ð/"ð/"ð/"ð/" ñ/"ô/"ð/"ð/"ð/"r