Instructions to use litert-community/Idol with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use litert-community/Idol with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Card: the denoiser did not compile for the Galaxy S26 NPU on the phone
Browse filesCompiled on the Galaxy S26 for its HTP (LiteRT 2.3.0, QAIRT 2.50), one denoiser block did not finish in 15 minutes at the default optimization level and ran out of memory after 28 s at optimization_level=1. Graph files unchanged.
README.md
CHANGED
|
@@ -244,6 +244,11 @@ the call.
|
|
| 244 |
- **Keep each GPU call short on the Galaxy S26.** In the feasibility run the VAE encoder ran as one graph, about 9 s
|
| 245 |
per GPU call; the screen compositor stalled and the process was killed (signal 9) on its fifth call. Every stage here
|
| 246 |
is split into several graphs for that reason (on the Galaxy S26 every GPU call takes 0.04–1.83 s: 45 graphs, 49 signatures).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 247 |
|
| 248 |
## Licence and provenance
|
| 249 |
|
|
|
|
| 244 |
- **Keep each GPU call short on the Galaxy S26.** In the feasibility run the VAE encoder ran as one graph, about 9 s
|
| 245 |
per GPU call; the screen compositor stalled and the process was killed (signal 9) on its fifth call. Every stage here
|
| 246 |
is split into several graphs for that reason (on the Galaxy S26 every GPU call takes 0.04–1.83 s: 45 graphs, 49 signatures).
|
| 247 |
+
- **The denoiser did not compile for the NPU on the phone.** Compiled on the Galaxy S26 for its NPU (Qualcomm HTP;
|
| 248 |
+
LiteRT 2.3.0, QAIRT 2.50), one denoiser block did not finish in 15 minutes at the default optimization level (O3)
|
| 249 |
+
and ran out of memory after 28 s at `optimization_level=1` (optimize for prepare); the HTP compiler warned it has
|
| 250 |
+
no tiling rule for the block's concatenations along the 12,294-token axis. In the shipped app every network but
|
| 251 |
+
BiRefNet (CPU) runs on the GPU.
|
| 252 |
|
| 253 |
## Licence and provenance
|
| 254 |
|