Spaces:
Sleeping
Sleeping
File size: 2,055 Bytes
e3af00f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
#!/usr/bin/env python3
# Copyright (c) 2022-2023, NVIDIA CORPORATION. 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.
"""Example with multiple models served on single Triton server."""
import logging
import numpy as np
from pytriton.decorators import batch
from pytriton.model_config import ModelConfig, Tensor
from pytriton.triton import Triton
logger = logging.getLogger("examples.multiple_models_python.server")
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(name)s: %(message)s")
@batch
def _multiply2(multiplicand):
product = multiplicand * 2.0
return [product]
@batch
def _multiply4(multiplicand):
product = multiplicand * 4.0
return [product]
with Triton() as triton:
logger.info("Loading Multiply2 model")
triton.bind(
model_name="Multiply2",
infer_func=_multiply2,
inputs=[
Tensor(name="multiplicand", dtype=np.float32, shape=(-1,)),
],
outputs=[
Tensor(name="product", dtype=np.float32, shape=(-1,)),
],
config=ModelConfig(max_batch_size=8),
strict=True,
)
logger.info("Loading Multiply4 model")
triton.bind(
model_name="Multiply4",
infer_func=_multiply4,
inputs=[
Tensor(name="multiplicand", dtype=np.float32, shape=(-1,)),
],
outputs=[
Tensor(name="product", dtype=np.float32, shape=(-1,)),
],
config=ModelConfig(max_batch_size=8),
strict=True,
)
triton.serve()
|