Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Kceshi #1850

Open
wants to merge 8 commits into
base: develop
Choose a base branch
from
Open

Kceshi #1850

Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
d4ac0ef
support nf4 channel wise quant & fix bug when blocksize>512 (#1817) (…
ceci3 Dec 19, 2023
dcf79e9
Add GroupWiseQuant & AWQ & AutoClip (#1821)
RachelXu7 Dec 26, 2023
521157e
[Cherry-Pick]Cp fit paddle26 (#1823)
RachelXu7 Dec 28, 2023
0df32a4
Merge branch 'release/2.6' of https://github.com/lizexu123/PaddleSlim…
lizexu123 Dec 29, 2023
c634106
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSlim …
lizexu123 Jan 23, 2024
e61ce8d
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSlim …
lizexu123 Feb 7, 2024
cdf10ef
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSlim …
lizexu123 Feb 23, 2024
9c3d105
测试
lizexu123 Feb 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions example/auto_compression/pytorch_yolo_series/cpp_infer/compile.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,10 +14,14 @@ WITH_MKL=ON
WITH_GPU=ON
USE_TENSORRT=ON

LIB_DIR=/root/auto_compress/Paddle/build/paddle_inference_install_dir/
# Paddle Inference预测库路径
LIB_DIR=/work/Paddle/build/paddle_inference_install_dir
# CUDNN路径
CUDNN_LIB=/usr/lib/x86_64-linux-gnu/
# CUDA路径
CUDA_LIB=/usr/local/cuda/lib64
TENSORRT_ROOT=/root/auto_compress/trt/trt8.4/
# TensorRT安装包路径，为TRT资源包解压后的绝对路径，其中包含lib和include文件夹
TENSORRT_ROOT=/work/TensorRT-8.6.1.6

WITH_ROCM=OFF
ROCM_LIB=/opt/rocm/lib
Expand All @@ -34,4 +38,4 @@ cmake .. -DPADDLE_LIB=${LIB_DIR} \
-DCUDA_LIB=${CUDA_LIB} \
-DTENSORRT_ROOT=${TENSORRT_ROOT}

make -j
make -j