TensorRT-LLMs/tensorrt_llm/runtime/__init__.py
Kaiyu Xie 9bd15f1937
TensorRT-LLM v0.10 update
* TensorRT-LLM Release 0.10.0

---------

Co-authored-by: Loki <lokravi@amazon.com>
Co-authored-by: meghagarwal <16129366+megha95@users.noreply.github.com>
2024-06-05 20:43:25 +08:00

52 lines
1.8 KiB
Python

# SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from .generation import SamplingConfig # autoflake: skip
from .generation import (ChatGLMGenerationSession, GenerationSession,
LogitsProcessor, LogitsProcessorList, ModelConfig,
QWenForCausalLMGenerationSession, StoppingCriteria,
StoppingCriteriaList, to_word_list_format)
from .kv_cache_manager import GenerationSequence, KVCacheManager
from .model_runner import ModelRunner
from .session import Session, TensorInfo
try:
import tensorrt_llm.bindings # NOQA
PYTHON_BINDINGS = True
except ImportError:
PYTHON_BINDINGS = False
if PYTHON_BINDINGS:
from .model_runner_cpp import ModelRunnerCpp
__all__ = [
'ModelConfig',
'GenerationSession',
'GenerationSequence',
'KVCacheManager',
'SamplingConfig',
'Session',
'TensorInfo',
'ChatGLMGenerationSession',
'QWenForCausalLMGenerationSession',
'to_word_list_format',
'LogitsProcessorList',
'LogitsProcessor',
'StoppingCriteriaList',
'StoppingCriteria',
'ModelRunner',
'ModelRunnerCpp',
'PYTHON_BINDINGS',
]