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.

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

Add stable-diffusion test on Linux #84

Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
25 commits
Select commit Hold shift + click to select a range
b796d7d
add stable-diffusion test on linux
wgzintel Dec 18, 2023
c6c9c16
Correct directory name for stable-diffusion
wgzintel Dec 18, 2023
6b7c344
refine test
wgzintel Dec 19, 2023
6b4d564
use stable-diffusion-v1-5 to test
wgzintel Dec 19, 2023
68d7452
only test statble-diffusion-v1-5
wgzintel Dec 19, 2023
24cc939
test juggernaut-xl on linux
wgzintel Dec 19, 2023
fd5c3d7
test stable-diffusion-nano-2-1 on linux
wgzintel Dec 19, 2023
826a042
Delete redundant git clone
wgzintel Dec 19, 2023
a5c7eab
test stable-diffusion-v1-4 on linux
wgzintel Dec 19, 2023
88c13cf
add stable-diffusion-v1-4 test on linux
wgzintel Dec 19, 2023
aba09ba
Merge branch 'master' of https://github.com/openvinotoolkit/openvino.…
wgzintel Dec 19, 2023
ffb1a4b
fix bug of llm_run_bloomz_560m_on_linux.sh
wgzintel Dec 19, 2023
fc141c9
fix stable-diffusion-v1-4 prompt file name
wgzintel Dec 19, 2023
e9e182a
Merge branch 'master' into guozhong/add_stable_diffusion_test
wgzintel Dec 19, 2023
18bf038
Merge branch 'master' into guozhong/add_stable_diffusion_test
wgzintel Dec 19, 2023
50562d2
add tiny-stable-diffusion-torch test on linux
wgzintel Dec 20, 2023
d63f611
do not use prompt file for stable-diffusion
wgzintel Dec 20, 2023
c548f6b
print total memory
wgzintel Dec 20, 2023
a423ea3
ulimit –c unlimited
wgzintel Dec 20, 2023
1631ebc
use tiny-sd for linux test
wgzintel Dec 21, 2023
6722961
remove ulimit –c unlimited
wgzintel Dec 21, 2023
ddd5fbb
Merge branch 'master' of https://github.com/openvinotoolkit/openvino.…
wgzintel Dec 21, 2023
bc44222
install openvino-nightly
peterchen-intel Dec 21, 2023
a556b1a
Convert with --stateful
peterchen-intel Dec 21, 2023
ae0ac56
Merge branch 'master' into guozhong/add_stable_diffusion_test
wgzintel Jan 1, 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
Prev Previous commit
Next Next commit
refine test
  • Loading branch information
wgzintel committed Dec 19, 2023
commit 6b7c344475080cade6b6a132bb6ec7f43811f257
8 changes: 8 additions & 0 deletions .github/workflows/llm_bench-python.yml
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,14 @@ jobs:
with:
name: llm.bench_diff
path: llm.bench_diff.diff
- name: Download test models
run: |
git lfs install
export GIT_LFS_SKIP_SMUDGE=0
git_clone_bloomz_560m="git clone https://huggingface.co/bigscience/bloomz-560m"
echo ${git_clone_bloomz_560m}
eval ${git_clone_bloomz_560m}
wait
- name: Run llm_bench test on linux
run: llm_bench/python/llm_run_on_linux.sh
stateful:
Expand Down
21 changes: 0 additions & 21 deletions llm_bench/python/llm_run_on_linux.sh
Original file line number Diff line number Diff line change
@@ -1,18 +1,6 @@
#!/bin/bash
# Copyright (C) 2023 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

git lfs install
export GIT_LFS_SKIP_SMUDGE=0
git_clone_bloomz_560m="git clone https://huggingface.co/bigscience/bloomz-560m"
echo ${git_clone_bloomz_560m}
eval ${git_clone_bloomz_560m}
wait

git_clone_stable_diff_2_1="git clone https://huggingface.co/stabilityai/stable-diffusion-2-1"
echo ${git_clone_stable_diff_2_1}
eval ${git_clone_stable_diff_2_1}
wait

convert_model="python ./llm_bench/python/convert.py --model_id bloomz-560m/ --output_dir ./ov_models/bloomz-560m --precision FP16"
echo ${convert_model}
Expand All @@ -21,13 +9,4 @@ wait

bemchmarking="python ./llm_bench/python/benchmark.py -m ./ov_models/bloomz-560m/pytorch/dldt/FP16/ -d cpu -n 1"
echo ${bemchmarking}
eval ${bemchmarking}

convert_model="python ./llm_bench/python/convert.py --model_id stable-diffusion-2-1/ --output_dir ./ov_models/stable-diffusion-v2-1 --precision FP16"
echo ${convert_model}
eval ${convert_model}
wait

bemchmarking="python ./llm_bench/python/benchmark.py -m ./ov_models/stable-diffusion-v2-1/pytorch/dldt/FP16/ -pf ./llm_bench/python/prompts/stable-diffusion-v2-1.jsonl -d cpu -n 1"
echo ${bemchmarking}
eval ${bemchmarking}