mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-31 11:56:44 +08:00
67990e0572
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
* Fastdeploy support min_p * add test_min_p * fix * min_p_sampling * update * delete vl_gpu_model_runner.py * fix * Align usage of min_p with vLLM * fix * modified unit test * fix test_min_sampling * pre-commit all files * fix * fix * fix * fix xpu_model_runner.py
49 lines
1.3 KiB
Python
49 lines
1.3 KiB
Python
"""
|
|
# Copyright (c) 2025 PaddlePaddle Authors. All Rights Reserved.
|
|
#
|
|
# 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 dataclasses import dataclass
|
|
from typing import Optional
|
|
|
|
import paddle
|
|
|
|
|
|
@dataclass
|
|
class SamplingMetadata:
|
|
"""
|
|
metadata for sampling.
|
|
"""
|
|
|
|
temperature: paddle.Tensor
|
|
|
|
pre_token_ids: paddle.Tensor
|
|
eos_token_ids: paddle.Tensor
|
|
frequency_penalties: paddle.Tensor
|
|
presence_penalties: paddle.Tensor
|
|
repetition_penalties: paddle.Tensor
|
|
|
|
min_dec_lens: paddle.Tensor
|
|
|
|
bad_words_token_ids: paddle.Tensor
|
|
|
|
step_idx: paddle.Tensor
|
|
|
|
top_p: paddle.Tensor
|
|
top_k: Optional[paddle.Tensor] = None
|
|
min_p: Optional[paddle.Tensor] = None
|
|
max_num_logprobs: Optional[int] = None
|
|
prompt_ids: Optional[paddle.Tensor] = None
|
|
prompt_lens: Optional[paddle.Tensor] = None
|