Uploaded using `kernel-builder`.
Browse files
README.md
CHANGED
|
@@ -1,14 +1,28 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
-
tags:
|
| 4 |
-
- kernels
|
| 5 |
---
|
| 6 |
|
| 7 |
-
|
| 8 |
|
| 9 |
-
##
|
| 10 |
|
| 11 |
-
|
|
|
|
|
|
|
| 12 |
|
| 13 |
-
|
|
|
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: kernels
|
| 3 |
license: apache-2.0
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
+
This is the repository card of kernels-community/quantization-eetq that has been pushed on the Hub. It was built to be used with the [`kernels` library](https://github.com/huggingface/kernels). This card was automatically generated.
|
| 7 |
|
| 8 |
+
## How to use
|
| 9 |
|
| 10 |
+
```python
|
| 11 |
+
# make sure `kernels` is installed: `pip install -U kernels`
|
| 12 |
+
from kernels import get_kernel
|
| 13 |
|
| 14 |
+
kernel_module = get_kernel("kernels-community/quantization-eetq")
|
| 15 |
+
w8_a16_gemm = kernel_module.w8_a16_gemm
|
| 16 |
|
| 17 |
+
w8_a16_gemm(...)
|
| 18 |
+
```
|
| 19 |
+
|
| 20 |
+
## Available functions
|
| 21 |
+
- `w8_a16_gemm`
|
| 22 |
+
- `w8_a16_gemm_`
|
| 23 |
+
- `preprocess_weights`
|
| 24 |
+
- `quant_weights`
|
| 25 |
+
|
| 26 |
+
## Benchmarks
|
| 27 |
+
|
| 28 |
+
No benchmark available yet.
|