mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
freeliuzc
cf7934a4b2
* optimize spec-inference architecture * delete debug log * optimize spec_method usage && fix unit_test * add claude unit-test skill * fix some ugly bug * enhance robustness and bounds check * unify method & spec_method to method to avoid bug * activate CI * fix unit test * Unify logprobs computation for naive and speculative decoding, fix CUDA kernel * fix logprob bug && optimize verify kernel * fix exist_decode() judge
22 lines
776 B
Python
22 lines
776 B
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.
|
|
"""
|
|
speculative decoding module
|
|
"""
|
|
|
|
from .base import Proposer
|
|
from .types import SpecMethod, VerifyStrategy
|
|
|
|
__all__ = ["Proposer", "SpecMethod", "VerifyStrategy"]
|