mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 00:33:03 +08:00
1e19833ba5
* [Feature] Add temp_scaled_logprobs and top_p_normalized_logprobs parameters for logits and logprobs post processing (#3552) * [feature] Add temp_scaled_logprobs and top_p_normalized_logprobs parameters for logits and logprobs post processing * infer engine support temp_scaled_logprobs and top_p_normalized_logprobs * delete some code * code check * code check and add doc * fix tokenizer.decoder(-1), return 'Invalid Token' * add ci for temp_scaled and top_p logprobs * check test * check seq len time shape * logprob clip inf --------- Co-authored-by: sunlei1024 <sunlei5788@gmail.com> * [Precision] Support lm_head layer running in float32 (#3597) * support lm_head fp32 bf16 fp16 * support lm_head fp32 bf16 fp16 * add doc and check code * lm_head_fp32 specify lm_head as fp32 * code check * check doc * code check --------- Co-authored-by: sunlei1024 <sunlei5788@gmail.com>
54 lines
1.6 KiB
Python
54 lines
1.6 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 Dict, 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
|
|
enable_early_stop: Optional[int] = False
|
|
stop_flags: Optional[paddle.Tensor] = None
|
|
prompt_ids: Optional[paddle.Tensor] = None
|
|
prompt_lens: Optional[paddle.Tensor] = None
|
|
temp_scaled_logprobs: Optional[paddle.Tensor] = None
|
|
top_p_normalized_logprobs: Optional[paddle.Tensor] = None
|
|
share_inputs: Optional[Dict[str, paddle.Tensor]] = None
|