Comments (5)
the --no-save_annotation
argument is exclusively used for the proprietary SHARK tuner, which is a separate piece of software that plugs into SHARK python for devs to tune models on. It's looking for a new home.
The .mlir should save to a temporary directory and be deleted after compilation, if they are persistent this is unintended and I can probably fix it quite easily. Can you tell me what the names/lifetimes of the files are like?
from shark.
Can you tell me what the names/lifetimes of the files are like?
Same name as the .vmfb stem, but with _torch_linalg.mlir
on the end. Same location as the .vmfb
Mode LastWriteTime Length Name
---- ------------- ------ ----
-a---- 31/10/2023 16:04 2084252845 unet512_1_77_768_512_fp16_tuned_cyberrealistic_v31_vulkan_torch_linalg.mlir
-a---- 30/10/2023 09:44 99031537 vae_1_77_512_512_fp16_tuned_cyberrealistic_v31_vulkan_torch_linalg.mlir
from shark.
I can confirm this behaviour for the 20231009_984 release. In my case the files are stored in the main folder. I did not realize this wasn't intended behaviour. So far the files are persistent over several days and restarts.
EBWebView
generated_imgs
models
shark_tank
shark_tmp
clip_1_64_512_512_fp16_tuned_v1-5-pruned_vulkan.vmfb
clip_1_64_512_512_fp16_tuned_v1-5-pruned_vulkan_torch_linalg.mlir
clip_1_64_512_512_fp16_v1-5-pruned_cpu.vmfb
clip_1_64_512_512_fp16_v1-5-pruned_cpu_torch_linalg.mlir
clip_1_64_512_512_fp16_v1-5-pruned_vulkan.vmfb
clip_1_64_512_512_fp16_v1-5-pruned_vulkan_torch_linalg.mlir
euler_scale_model_input_1_512_512_cpu_fp16.vmfb
euler_scale_model_input_1_512_512_rocm_fp16.vmfb
euler_scale_model_input_1_512_512_vulkan_fp16.vmfb
euler_step_1_512_512_cpu_fp16.vmfb
euler_step_1_512_512_vulkan_fp16.vmfb
nodai_shark_studio_20231009_984.exe
unet_1_64_512_512_fp16_tuned_v1-5-pruned_vulkan.vmfb
unet_1_64_512_512_fp16_tuned_v1-5-pruned_vulkan_torch_linalg.mlir
unet_1_64_512_512_fp16_v1-5-pruned_cpu.vmfb
unet_1_64_512_512_fp16_v1-5-pruned_cpu_torch_linalg.mlir
unet_1_64_512_512_fp16_v1-5-pruned_vulkan.vmfb
unet_1_64_512_512_fp16_v1-5-pruned_vulkan_torch_linalg.mlir
vae_1_64_512_512_fp16_tuned_v1-5-pruned_vulkan.vmfb
vae_1_64_512_512_fp16_tuned_v1-5-pruned_vulkan_torch_linalg.mlir
vae_1_64_512_512_fp16_v1-5-pruned_cpu.vmfb
vae_1_64_512_512_fp16_v1-5-pruned_cpu_torch_linalg.mlir
vae_1_64_512_512_fp16_v1-5-pruned_vulkan.vmfb
vae_1_64_512_512_fp16_v1-5-pruned_vulkan_torch_linalg.mlir
variants.json
from shark.
I have moved the "intermediary" mlir files to be saved in the ./shark_tmp/
directory. d051c3a
Previously, the .mlir was saved in whichever directory the tempfile
module uses by default. It seems for windows this registered as $PWD
(explaining the behavior seen in this issue) and on Linux it was /tmp/
, which causes issues for some users running without root-level permissions.
Ideally we have an option that cleans up this directory at shutdown or after .vmfb compilation, but I'm open to suggestions here.
from shark.
We already do a cleanup of ./shark_tmp
for gradio temporary image files from the previous run on studio startup. I'll put up a PR that adds .mlir
to that.
After compilation would be cleaner, of course.
from shark.
Related Issues (20)
- running SDXL set to 1024x1024 renders a black image
- AMD bought you guys but I have to downgrade GPU drivers to one year ago? HOT 2
- "Could not compile Unet. Please create an issue with the detailed log....
- "Could not compile Unet. Please create an issue with the detailed log...." HOT 4
- Shared memory issues with SD on Vulkan HOT 2
- Issue with VAE decode on Windows
- ModuleNotFoundError: No module named 'apps' HOT 16
- [BUG][Pre-release] ImportError: cannot import name 'ParameterIndexEntry' from 'iree.runtime'
- AMD Rocm windows does not work - hipErrorSharedObjectInitFailed
- SDXL Support for 2.0
- Custom model support HOT 1
- Documentation for 2.0
- File system cleanup for 2.0 HOT 1
- Custom LORA support
- Llama2 in 2.0
- Stuck at "Compiling Vulkan shaders" (or takes forever?) HOT 2
- How to change upscaler model?
- how to export tosa/linalg, when conv input and weight are torch.int8, bias is torch.int32
- Wrong SDXL1.0 HuggingFace Repository
- Error creating vm context with modules... on RX 580
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 shark.