Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add input and output tokens to response #41

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add input and output tokens to response #41

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 22 additions & 3 deletions src/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,11 @@ def auto_complete_config(auto_complete_model_config):
"optional": True,
},
]
outputs = [{"name": "text_output", "data_type": "TYPE_STRING", "dims": [-1]}]
outputs = [
{"name": "text_output", "data_type": "TYPE_STRING", "dims": [-1]},
{"name": "input_tokens", "data_type": "TYPE_INT32", "dims": [-1]},
{"name": "output_tokens", "data_type": "TYPE_INT32", "dims": [-1]},
]

# Store the model configuration as a dictionary.
config = auto_complete_model_config.as_dict()
Expand Down Expand Up @@ -108,6 +112,14 @@ def initialize(self, args):
self.model_config, "text_output"
)
self.output_dtype = pb_utils.triton_string_to_numpy(output_config["data_type"])
output_tokens_config = pb_utils.get_output_config_by_name(
self.model_config, "output_tokens"
)
self.output_tokens_dtype = pb_utils.triton_string_to_numpy(output_tokens_config["data_type"])
input_tokens_config = pb_utils.get_output_config_by_name(
self.model_config, "input_tokens"
)
self.input_tokens_dtype = pb_utils.triton_string_to_numpy(input_tokens_config["data_type"])

# Prepare vLLM engine
self.init_engine()
Expand Down Expand Up @@ -313,10 +325,17 @@ def create_response(self, vllm_output, prepend_input):
text_outputs = [
(prompt + output.text).encode("utf-8") for output in vllm_output.outputs
]
output_tokens = sum([len(output.token_ids) for output in vllm_output.outputs])
triton_output_tensor = pb_utils.Tensor(
"text_output", np.asarray(text_outputs, dtype=self.output_dtype)
"text_output", np.asarray(text_outputs, dtype=self.output_dtype),
)
return pb_utils.InferenceResponse(output_tensors=[triton_output_tensor])
triton_tokens_tensor = pb_utils.Tensor(
"output_tokens", np.asarray(output_tokens, dtype=self.output_tokens_dtype),
)
triton_input_tokens_tensor = pb_utils.Tensor(
"input_tokens", np.asarray(len(vllm_output.prompt_token_ids), dtype=self.input_tokens_dtype),
)
return pb_utils.InferenceResponse(output_tensors=[triton_output_tensor, triton_tokens_tensor, triton_input_tokens_tensor])
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This would also need to be done for the create_stream_response function, so the usage outputs are also present in stream responses.


def create_stream_response(self, vllm_output, previous_outputs_lengths):
"""
Expand Down