Vollo Compiler API Reference

• vollo_compiler
  • Config
    • Config.ia_420f_c6b32()
    • Config.ia_840f_c3b64()
    • Config.save()
    • Config.load()
    • Config.block_size
    • Config.num_cores
    • Config.tensor_ram_depth
    • Config.tensor_descriptor_count
    • Config.weight_store_depth
    • Config.accum_store_depth
    • Config.cell_state_depth
    • Config.clamp_store_depth
    • Config.max_read_size
    • Config.io_size
  • NNIR
    • NNIR.from_onnx()
    • NNIR.streaming_transform()
    • NNIR.to_program()
    • NNIR.__new__()
  • Program
    • Program.compute_duration_per_inference_us()
    • Program.cycle_count_per_inference()
    • Program.hw_config()
    • Program.io_only_test()
    • Program.load()
    • Program.load_bytes()
    • Program.metrics()
    • Program.model_input_shape()
    • Program.model_input_streaming_dim()
    • Program.model_num_inputs()
    • Program.model_num_outputs()
    • Program.model_output_shape()
    • Program.model_output_streaming_dim()
    • Program.num_models()
    • Program.save()
    • Program.save_bytes()
    • Program.to_vm()
    • Program.transform_to_io_only_test()
  • ProgramBuilder
    • ProgramBuilder.add_nnir()
    • ProgramBuilder.to_program()
  • Metrics
    • Metrics.clamp_store_depth
    • Metrics.clamp_store_used
    • Metrics.input_bytes
    • Metrics.model_names
    • Metrics.num_instrs
    • Metrics.output_bytes
    • Metrics.tensor_ram_depth
    • Metrics.tensor_ram_used
    • Metrics.weight_store_depth
    • Metrics.weight_store_used
  • VM
    • VM.compute_duration_us()
    • VM.cycle_count()
    • VM.metrics()
    • VM.run()
    • VM.run_flat()
    • VM.run_flat_timesteps()
    • VM.run_timesteps()
  • AllocationError
  • SaveError
  • LoadError
• vollo_torch
  • vollo_torch.fx
    • save()
    • load()
  • vollo_torch.nn
    • PaddedConv1d
    • LSTM
    • RecurrentStateLSTM
    • LSTMCell
      • LSTMCell.forward()
      • LSTMCell.reset()
    • Ones
    • Zeros
    • Scan
      • Scan.forward()
    • RMSNorm
      • RMSNorm.extra_repr()
• vollo_rt
  • VolloRTContext
    • VolloRTContext.accelerator_block_size()
    • VolloRTContext.accelerator_num_cores()
    • VolloRTContext.add_accelerator()
    • VolloRTContext.add_job()
    • VolloRTContext.add_job_bf16()
    • VolloRTContext.add_job_f32()
    • VolloRTContext.add_vm()
    • VolloRTContext.get_result()
    • VolloRTContext.load_program()
    • VolloRTContext.load_program_bytes()
    • VolloRTContext.model_input_shape()
    • VolloRTContext.model_input_streaming_dim()
    • VolloRTContext.model_name()
    • VolloRTContext.model_num_inputs()
    • VolloRTContext.model_num_outputs()
    • VolloRTContext.model_output_shape()
    • VolloRTContext.model_output_streaming_dim()
    • VolloRTContext.num_models()
    • VolloRTContext.poll()
    • VolloRTContext.run()