MCPcopy
hub / github.com/NVIDIA/TensorRT-LLM / run.py

File run.py

examples/models/core/bert/run.py:None–None  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

1# SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2# SPDX-License-Identifier: Apache-2.0
3#
4# Licensed under the Apache License, Version 2.0 (the "License");

Callers

nothing calls this directly

Calls 15

get_engine_nameFunction · 0.90
temporary_datasets_configFunction · 0.90
prepare_text_inputsFunction · 0.90
process_inputFunction · 0.90
TensorInfoClass · 0.90
trt_dtype_to_torchFunction · 0.90
intermediate_checkFunction · 0.90
decode_bertqa_outputFunction · 0.90
compare_bertqa_resultFunction · 0.90
decode_bertcls_outputFunction · 0.90
compare_bertcls_resultFunction · 0.90
set_levelMethod · 0.80

Tested by

no test coverage detected