o j9:j&@sBddlZdgZeZdZeejdrejjZdZGdddeZdS)N GreenContextF_CUDAGreenContextTc seZdZdZeddddddedBdedBdedBdedBdef d d ZeddedBdefd d Z dfd d Z dfdd Z dfdd Z Z S)rzyWrapper around a CUDA green context. .. warning:: This API is in beta and may change in future releases. Nnum_smsworkqueue_scopeworkqueue_concurrency_limit device_idrrrrreturncCststdtj||||dS)a+Create a CUDA green context. At least one of ``num_sms`` or ``workqueue_scope`` must be specified. Both can be combined to partition SMs and configure workqueues in the same green context. Arguments: num_sms (int, optional): The number of SMs to use in the green context. When ``None``, SMs are not partitioned. workqueue_scope (str, optional): Workqueue sharing scope. One of ``"device_ctx"`` (shared across all contexts, default driver behaviour) or ``"balanced"`` (non-overlapping workqueues with other balanced green contexts). When ``None``, no workqueue configuration is applied. workqueue_concurrency_limit (int, optional): Maximum number of concurrent stream-ordered workloads for the workqueue. Requires ``workqueue_scope`` to be set. device_id (int, optional): The device index of green context. When ``None``, the current device is used. 1PyTorch was not built with Green Context support!)rrrr) SUPPORTED RuntimeError _GreenContextcreaterr`/home/nk/hobo-godmode/plappi-mvp/.venv/lib/python3.10/site-packages/torch/cuda/green_contexts.pyrszGreenContext.createcCststdtj|dS)awReturn the maximum workqueue concurrency limit for the device. This queries the device for the default number of concurrent stream-ordered workloads supported by workqueue configuration resources. Arguments: device_id (int, optional): The device index to query. When ``None``, the current device is used. r r)r r r max_workqueue_concurrencyrrrrr>s  z&GreenContext.max_workqueue_concurrencyc tS)z+Make the green context the current context.)super set_contextself __class__rrrP zGreenContext.set_contextcr)zAssuming the green context is the current context, pop it from the context stack and restore the previous context. )r pop_contextrrrrrTs zGreenContext.pop_contexttorch.cuda.Streamcr)z1Return the CUDA Stream used by the green context.)rStreamrrrrrZrzGreenContext.Stream)N)r N)r r)__name__ __module__ __qualname____doc__ staticmethodintstrr rrrrr __classcell__rrrrrs. $) torch__all__objectr r hasattr_Crrrrrrs