triton.Config

class triton.Config(kwargs, num_warps=4, num_stages=2, num_ctas=1, num_buffers_warp_spec=0, num_consumer_groups=0, reg_dec_producer=0, reg_inc_consumer=0, maxnreg=None, pre_hook=None)

An object that represents a possible kernel configuration for the auto-tuner to try.

Variables:

  • kwargs – a dictionary of meta-parameters to pass to the kernel as keyword arguments.

  • num_warps – the number of warps to use for the kernel when compiled for GPUs. For example, if num_warps=8, then each kernel instance will be automatically parallelized to cooperatively execute using 8 * 32 = 256 threads.

  • num_stages – the number of stages that the compiler should use when software-pipelining loops. Mostly useful for matrix multiplication workloads on SM80+ GPUs.

  • num_ctas – number of blocks in a block cluster. SM90+ only.

  • maxnreg – maximum number of registers one thread can use. Corresponds to ptx .maxnreg directive. Not supported on all platforms.

  • pre_hook – a function that will be called before the kernel is called. Parameters of this function are args.

__init__(kwargs, num_warps=4, num_stages=2, num_ctas=1, num_buffers_warp_spec=0, num_consumer_groups=0, reg_dec_producer=0, reg_inc_consumer=0, maxnreg=None, pre_hook=None)

Methods

__init__(kwargs[, num_warps, num_stages, ...])

all_kwargs()