Instructions to use replicate/quantization-eetq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/quantization-eetq with Kernels:
# !pip install kernels from kernels import get_kernel # a version (or an explicit revision) is required; see the "Files and versions" tab for the available ones kernel = get_kernel("replicate/quantization-eetq", version=1) - Notebooks
- Google Colab
- Kaggle
Download utils/cuda_utils.cc from replicate/quantization-eetq: direct link, hf CLI and curl.
- Browser
- Download file 1.6 kB
-
https://huggingface.co/replicate/quantization-eetq/resolve/8f7b5f05c1eef6061e33b4e67ce888eb3e558e44/utils/cuda_utils.cc
- Command line
-
hf download hf://replicate/quantization-eetq@8f7b5f05c1eef6061e33b4e67ce888eb3e558e44/utils/cuda_utils.cc
-
curl -L -o cuda_utils.cc https://huggingface.co/replicate/quantization-eetq/resolve/8f7b5f05c1eef6061e33b4e67ce888eb3e558e44/utils/cuda_utils.cc
1.6 kB
| /* | |
| * Copyright (c) 2019-2023, 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. | |
| */ | |
| namespace fastertransformer { | |
| /* ***************************** common utils ****************************** */ | |
| cudaError_t getSetDevice(int i_device, int* o_device) | |
| { | |
| int current_dev_id = 0; | |
| cudaError_t err = cudaSuccess; | |
| if (o_device != NULL) { | |
| err = cudaGetDevice(¤t_dev_id); | |
| if (err != cudaSuccess) { | |
| return err; | |
| } | |
| if (current_dev_id == i_device) { | |
| *o_device = i_device; | |
| } | |
| else { | |
| err = cudaSetDevice(i_device); | |
| if (err != cudaSuccess) { | |
| return err; | |
| } | |
| *o_device = current_dev_id; | |
| } | |
| } | |
| else { | |
| err = cudaSetDevice(i_device); | |
| if (err != cudaSuccess) { | |
| return err; | |
| } | |
| } | |
| return cudaSuccess; | |
| } | |
| /* ************************** end of common utils ************************** */ | |
| } // namespace fastertransformer | |