tensorrt_llm_bls/config.pbtxt

# Copyright 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
#  * Redistributions of source code must retain the above copyright
#    notice, this list of conditions and the following disclaimer.
#  * Redistributions in binary form must reproduce the above copyright
#    notice, this list of conditions and the following disclaimer in the
#    documentation and/or other materials provided with the distribution.
#  * Neither the name of NVIDIA CORPORATION nor the names of its
#    contributors may be used to endorse or promote products derived
#    from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

name: "tensorrt_llm_bls"
backend: "python"
max_batch_size: 32

model_transaction_policy {
  decoupled: True
}

input [
  {
    name: "text_input"
    data_type: TYPE_STRING
    dims: [ 1 ]
  },
  {
    name: "decoder_text_input"
    data_type: TYPE_STRING
    dims: [ 1 ]
    optional: true
  },
  {
    name: "image_input"
    data_type: TYPE_FP16
    dims: [ -1, 3, -1, -1 ]
    optional: true
  },
  {
    name: "image_bytes_input"
    data_type: TYPE_UINT8
    dims: [ -1, -1, -1, -1 ]
    optional: true
  },
  {
    name: "image_url_input"
    data_type: TYPE_STRING
    dims: [ 1 ]
    optional: true
  },
  {
    name: "video_bytes_input"
    data_type: TYPE_UINT8
    dims: [ -1, -1, -1, -1 ]
    optional: true
  },
  {
    name: "max_tokens"
    data_type: TYPE_INT32
    dims: [ 1 ]
  },
  {
   name: "bad_words"
   data_type: TYPE_STRING
   dims: [ -1 ]
   optional: true
  },
  {
   name: "stop_words"
   data_type: TYPE_STRING
   dims: [ -1 ]
   optional: true
  },
  {
    name: "exclude_input_in_output"
    data_type: TYPE_BOOL
    dims: [ 1 ]
    optional: true
  },
  {
    name: "end_id"
    data_type: TYPE_INT32
    dims: [ 1 ]
    optional: true
  },
  {
    name: "pad_id"
    data_type: TYPE_INT32
    dims: [ 1 ]
    optional: true
  },
  {
    name: "top_k"
    data_type: TYPE_INT32
    dims: [ 1 ]
    optional: true
  },
  {
    name: "top_p"
    data_type: TYPE_FP32
    dims: [ 1 ]
    optional: true
  },
  {
    name: "temperature"
    data_type: TYPE_FP32
    dims: [ 1 ]
    optional: true
  },
  {
    name: "length_penalty"
    data_type: TYPE_FP32
    dims: [ 1 ]
    optional: true
  },
  {
    name: "repetition_penalty"
    data_type: TYPE_FP32
    dims: [ 1 ]
    optional: true
  },
  {
    name: "min_length"
    data_type: TYPE_INT32
    dims: [ 1 ]
    optional: true
  },
  {
    name: "presence_penalty"
    data_type: TYPE_FP32
    dims: [ 1 ]
    optional: true
  },
  {
    name: "frequency_penalty"
    data_type: TYPE_FP32
    dims: [ 1 ]
    optional: true
  },
  {
    name: "random_seed"
    data_type: TYPE_UINT64
    dims: [ 1 ]
    optional: true
  },
  {
    name: "return_log_probs"
    data_type: TYPE_BOOL
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "return_context_logits"
    data_type: TYPE_BOOL
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "return_generation_logits"
    data_type: TYPE_BOOL
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "num_return_sequences"
    data_type: TYPE_INT32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "beam_width"
    data_type: TYPE_INT32
    dims: [ 1 ]
    optional: true
  },
  {
    name: "stream"
    data_type: TYPE_BOOL
    dims: [ 1 ]
    optional: true
  },
  {
    name: "prompt_embedding_table"
    data_type: TYPE_FP16
    dims: [ -1, -1 ]
    optional: true
  },
  {
    name: "prompt_vocab_size"
    data_type: TYPE_INT32
    dims: [ 1 ]
    optional: true
  },
  {
    name: "prompt_table_extra_id"
    data_type: TYPE_UINT64
    dims: [ 1 ]
    optional: true
  },
  {
      name: "embedding_bias_words"
      data_type: TYPE_STRING
      dims: [ -1 ]
      optional: true
  },
  {
      name: "embedding_bias_weights"
      data_type: TYPE_FP32
      dims: [ -1 ]
      optional: true
  },
  {
      name: "num_draft_tokens",
      data_type: TYPE_INT32,
      dims: [ 1 ]
      optional: true
  },
  {
      name: "use_draft_logits",
      data_type: TYPE_BOOL,
      dims: [ 1 ]
      reshape: { shape: [ ] }
      optional: true
  },
  # the unique task ID for the given LoRA.
  # To perform inference with a specific LoRA for the first time `lora_task_id` `lora_weights` and `lora_config` must all be given.
  # The LoRA will be cached, so that subsequent requests for the same task only require `lora_task_id`.
  # If the cache is full the oldest LoRA will be evicted to make space for new ones.  An error is returned if `lora_task_id` is not cached.
  {
    name: "lora_task_id"
	data_type: TYPE_UINT64
	dims: [ 1 ]
    reshape: { shape: [ ] }
	optional: true
  },
  # weights for a lora adapter shape [ num_lora_modules_layers, D x Hi + Ho x D ]
  # where the last dimension holds the in / out adapter weights for the associated module (e.g. attn_qkv) and model layer
  # each of the in / out tensors are first flattened and then concatenated together in the format above.
  # D=adapter_size (R value), Hi=hidden_size_in, Ho=hidden_size_out.
  {
    name: "lora_weights"
	data_type: TYPE_FP16
	dims: [ -1, -1 ]
	optional: true
	allow_ragged_batch: true
  },
  # module identifier (same size a first dimension of lora_weights)
  # See LoraModule::ModuleType for model id mapping
  #
  # "attn_qkv": 0     # compbined qkv adapter
  # "attn_q": 1       # q adapter
  # "attn_k": 2       # k adapter
  # "attn_v": 3       # v adapter
  # "attn_dense": 4   # adapter for the dense layer in attention
  # "mlp_h_to_4h": 5  # for llama2 adapter for gated mlp layer after attention / RMSNorm: up projection
  # "mlp_4h_to_h": 6  # for llama2 adapter for gated mlp layer after attention / RMSNorm: down projection
  # "mlp_gate": 7     # for llama2 adapter for gated mlp later after attention / RMSNorm: gate
  #
  # last dim holds [ module_id, layer_idx, adapter_size (D aka R value) ]
  {
    name: "lora_config"
	data_type: TYPE_INT32
	dims: [ -1, 3 ]
	optional: true
	allow_ragged_batch: true
  },
  {
    name: "return_kv_cache_reuse_stats"
    data_type: TYPE_BOOL
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "guided_decoding_guide_type"
    data_type: TYPE_STRING
    dims: [ 1 ]
    optional: true
  },
  {
    name: "guided_decoding_guide"
    data_type: TYPE_STRING
    dims: [ 1 ]
    optional: true
  }
]
output [
  {
    name: "text_output"
    data_type: TYPE_STRING
    dims: [ -1 ]
  },
  {
    name: "cum_log_probs"
    data_type: TYPE_FP32
    dims: [ -1 ]
  },
  {
    name: "output_log_probs"
    data_type: TYPE_FP32
    dims: [ -1, -1 ]
  },
  {
    name: "context_logits"
    data_type: TYPE_FP16
    dims: [ -1, -1 ]
  },
  {
    name: "generation_logits"
    data_type: TYPE_FP16
    dims: [ -1, -1, -1 ]
  },
  {
    name: "batch_index"
    data_type: TYPE_INT32
    dims: [ 1 ]
  },
  {
    name: "sequence_index"
    data_type: TYPE_INT32
    dims: [ 1 ]
  },
  {
    name: "kv_cache_alloc_new_blocks"
    data_type: TYPE_INT32
    dims: [ 1 ]
  },
  {
    name: "kv_cache_reused_blocks"
    data_type: TYPE_INT32
    dims: [ 1 ]
  },
  {
    name: "kv_cache_alloc_total_blocks"
    data_type: TYPE_INT32
    dims: [ 1 ]
  }
]

parameters: {
  key: "accumulate_tokens"
  value: {
    string_value: "${accumulate_tokens}"
  }
}
parameters: {
  key: "tensorrt_llm_model_name"
  value: {
    string_value: "tensorrt_llm"
  }
}
parameters: {
  key: "tensorrt_llm_draft_model_name"
  value: {
    string_value: "${tensorrt_llm_draft_model_name}"
  }
}
parameters: {
  key: "multimodal_encoders_name"
  value: {
    string_value: "${multimodal_encoders_name}"
  }
}

instance_group [
  {
    count: 1
    kind : KIND_CPU
  }
]