flashinfer.fused_moe.CuTileFp8PerTensorBf16Runner

class flashinfer.fused_moe.CuTileFp8PerTensorBf16Runner(config: MoEConfig, device: device)

__init__(config: MoEConfig, device: device)

Methods

__init__(config, device)
build()
check_support()
forward(inputs[, tactic, do_preparation])	Forward pass for tunable runners.
get_cache_key_extras(inputs)	Return extra values to include in the autotune cache key.
get_valid_tactics(inputs, _profile)	One tactic corresponding to one cuda kernel normally, but how to interpret the meaning of tactic is pure internal details of the runner.
launch_kwargs_for(inputs)	Return only the launch kwargs required by this packed call.
launch_state_for(inputs)	Return immutable per-call launch metadata paired with inputs.
pack_inputs(act, weights)
precompile_tactics(inputs, tactics, profile, ...)	Optionally perform compile-only work for all tactics before profiling.
supports_quant(quant)	Return whether this runner can execute quant's three format axes.
tuning_config_for(inputs)	Return the tuning config paired with inputs when one is present.

Attributes

backend_key
supported_activation_classes
supported_activation_classes_by_quant
supported_output_formats
supported_quant_variants
supported_routing_modes
supports_expert_parallelism
supports_fused_shared_experts
supports_nvfp4_4over6
config