-
**Describe the bug**
A clear and concise description of what the bug is.
I ran two distinct experiments, one on uniform quantization, and one on channel pruning with the same resnet model, however, …
-
![Screenshot 2024-07-10 191928](https://github.com/mc2-project/delphi/assets/71505949/9bfdbbf5-efe5-411c-8a4e-b0867215d861)
-
https://deepmind.google/discover/blog/alphageometry-an-olympiad-level-ai-system-for-geometry/
https://manifestai.com/blogposts/faster-after-all/
https://www.theverge.com/2024/1/18/24042354/mark-zu…
-
I have been making some benchmarks with Marlin, but the speed-up is far from what is reported. In fact, it's actually slower than fp16:
GPU: A6000 ada
```
matrix_shape: [11008, 4096]
input_s…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
tf 2.14.0
### Custom code
Yes
### OS platform and distribution
Ubunt…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
tf 2.14.0
### Custom code
Yes
### OS platform and distribution
Ubunt…
-
I run demo 1st time in google colab and it's working, but when i try 2th time the demo is not working. This is what I got:
`
Warning: If you want to use fp16, please apex with cuda support (https:…
-
![image](https://user-images.githubusercontent.com/5450325/85355941-3cc06e80-b540-11ea-8399-4376c40da9b6.png)
In paper, I see the great difference between the patch input and resize input. but in cod…
-
### Describe the issue
when using yolov8 fp32 onnx model by qnn, it runs successfully in Snapdragon 8 Gen 2 (SM8550 pnone: redme k70),but it run failedly in Snapdragon 8888 (SM8350 phone: realme gt…
-
I'd be very interested in how we could take llm.c models and export them into universal formats, e.g. for very fast inference in llama.cpp, vllm, or etc. Or how they could be made HuggingFace compat…