Comments (8)
I'm having the same issue.
This used to work (a week ago) with checkout 1004acaa3a5c0f515a3f7b229aef1dabe31472a4
. Now I tried rebuilding on another machine (Debian, incidentally, but it shouldn't matter) to try the LLM functions and the 579de32260742a24166ecd13213d2e60af862675
checkout doesn't work, so there's probably a third "good" checkout that makes sense.
@vitoplantamura, can you go back and check your build tree?
from onnxstream.
from onnxstream.
I'm build XnnPack from this:
git clone https://github.com/google/XNNPACK.git
cd XNNPACK
git checkout 579de32260742a24166ecd13213d2e60af862675
mkdir build
cd build
cmake -DXNNPACK_BUILD_TESTS=OFF -DXNNPACK_BUILD_BENCHMARKS=OFF ..
cmake --build . --config Release
Then try build:
git clone https://github.com/vitoplantamura/OnnxStream.git
cd OnnxStream
cd src
mkdir build
cd build
cmake -DMAX_SPEED=ON -DOS_LLM=OFF -DOS_CUDA=OFF -DXNNPACK_DIR=/media/usb_hard_drive/genimage/XNNPACK/ ..
cmake --build . --config Release
when I enter git checkout 579de32260742a24166ecd13213d2e60af862675
, I get the following output
git checkout 579de32260742a24166ecd13213d2e60af862675
Note: switching to '579de32260742a24166ecd13213d2e60af862675'.
You are in 'detached HEAD' state. You can look around, make experimental
changes and commit them, and you can discard any commits you make in this
state without impacting any branches by switching back to a branch.
If you want to create a new branch to retain commits you create, you may
do so (now or later) by using -c with the switch command. Example:
git switch -c <new-branch-name>
Or undo this operation with:
git switch -
Turn off this advice by setting config variable advice.detachedHead to false
HEAD is now at 579de3226 Refactor `xnn_indirection_init_dwconv2d` to take low-level arguments.
from onnxstream.
hi,
I tried in Google Colab and it works:
# build XNNPACK (takes 22 minutes, Colab Free NO GPU)
!git clone https://github.com/google/XNNPACK.git && cd XNNPACK && git checkout 579de32260742a24166ecd13213d2e60af862675 && mkdir build && cd build && cmake -DXNNPACK_BUILD_TESTS=OFF -DXNNPACK_BUILD_BENCHMARKS=OFF .. && cmake --build . --config Release --parallel 6
# build OnnxStream (Stable Diffusion example, takes 1 minute)
!git clone https://github.com/vitoplantamura/OnnxStream.git && cd OnnxStream && cd src && mkdir build && cd build && cmake -DMAX_SPEED=ON -DOS_LLM=OFF -DOS_CUDA=OFF -DXNNPACK_DIR=/content/XNNPACK .. && cmake --build . --config Release
# run with this command
!/content/OnnxStream/src/build/sd
@pavelprosto94: Could you do a "git pull" in your local OnnxStream repo and try again?
@rcarmo: What is the error exactly?
Thanks, Vito
from onnxstream.
Same thing, a set of invalid conversions. I will try again ASAP.
from onnxstream.
I do not know what commands I need to enter. I don't know Git well
I tried this:
cd XNNPACK
git pull
output:
You are not currently on a branch.
Please specify which branch you want to merge with.
See git-pull(1) for details.
git pull <remote> <branch>
And Google Colab don't work with arm64. XNNPACK compiles different versions for arm64 and x86-64
from onnxstream.
from onnxstream.
I'm use this fork https://github.com/AeroX2/OnnxStream
mkdir onnxstream
cd onnxstream
build XNNPACK:
git clone https://github.com/google/XNNPACK.git
cd XNNPACK
git rev-list -n 1 --before="2023-06-27 00:00" master
git checkout <COMMIT_ID_FROM_THE_PREVIOUS_COMMAND>
mkdir build
cd build
cmake -DXNNPACK_BUILD_TESTS=OFF -DXNNPACK_BUILD_BENCHMARKS=OFF ..
cmake --build . --config Release
Then build fork OnnxStream:
git clone https://github.com/AeroX2/OnnxStream.git
cd OnnxStream
cd src
mkdir build
cd build
cmake -DMAX_SPEED=ON -DXNNPACK_DIR=<DIRECTORY_WHERE_XNNPACK_WAS_CLONED> ..
cmake --build . --config Release
and it work! Thank!
For OrangePi 5, one image is generated in 2 minutes. A wonderful result!
from onnxstream.
Related Issues (20)
- [FEATURE REQUEST] LCM Sampler
- Errors with ./sd HOT 1
- [feature request] image 2 image?
- [feature request] Whisper with openblas HOT 3
- [question] your Mistral-to-ONNX export script HOT 2
- [question] why to convert model from ONNX to TXT format? HOT 1
- Username and password required? HOT 1
- How open are you to code-refactoring Pull Requests? HOT 2
- Stable Diffisuon 1.5 installation from? HOT 3
- changing image size HOT 2
- UnsupportedOperatorError: Exporting the operator ::_transformer_encoder_layer_fwd to ONNX opset HOT 2
- Tensor memory layout HOT 7
- Add support for 1 step diffusion (DMD) HOT 1
- vae_decoder_qu8/range_data.txt value generation HOT 1
- Pi Zero 2w 32bit build of xnnpack failing HOT 7
- Onnxstream won't build HOT 2
- 403 error HOT 1
- Safetensors? HOT 4
- Any updates in generating dynamic shape images? HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from onnxstream.