nemo_automodel.components.models.qwen3_8_flash_next.backend

class nemo_automodel.components.models.qwen3_8_flash_next.backend.Qwen3_8_FlashNextBackendConfig(
    attn: typing.Literal['te', 'sdpa', 'flex', 'eager', 'tilelang', 'cudnn', 'cute'] = BackendConfig.attn,
    sparse_attn: typing.Literal['generic', 'msa'] = 'generic',
    linear: typing.Literal['torch', 'te', 'quack'] = 'te' if HAVE_TE and torch.c...,
    rms_norm: typing.Literal['torch', 'torch_fp32', 'te', 'quack'] = 'torch_fp32',
    rope: typing.Literal['torch', 'quack'] = 'torch',
    rope_fusion: bool = HAVE_TE and torch.cuda.is_a...,
    experts: typing.Literal['torch', 'te', 'gmm', 'torch_mm', 'torch_mm_mxfp8'] = 'torch_mm' if torch.cuda.is...,
    dispatcher: typing.Literal['torch', 'deepep', 'hybridep', 'uccl_ep', 'mok'] = 'deepep' if HAVE_DEEP_EP an...,
    dispatcher_num_sms: int = 20,
    dispatcher_share_token_dispatcher: bool = True,
    dispatcher_async_dispatch: bool = False,
    mok: nemo_automodel.components.models.common.utils.MoKBackendConfig = MoKBackendConfig(),
    enable_deepep: bool | None = None,
    fake_balanced_gate: bool = False,
    fake_gate_noise: float = 0.0,
    enable_hf_state_dict_adapter: bool = True,
    enable_fsdp_optimizations: bool = False,
    te_fp8: nemo_automodel.components.models.common.utils.TEFp8Config | None = None,
    gate_precision: str | torch.dtype | None = None,
    compile_attn: bool = False,
    compile_situ: bool = False,
    compile_norm: bool = False,
    shared_expert_overlap: bool = False,
    compile_router_weight: bool = False,
    benchmark_static_routing: bool = False,
    cuda_graph: nemo_automodel.components.models.common.utils.CudaGraphConfig = CudaGraphConfig()
)