Kernels:
Trusted publisher
Uploaded using `kernel-builder`.
Browse files
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: kernels
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
This is the repository card of kernels-community/finegrained-fp8 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/finegrained-fp8", version=3)
|
| 15 |
+
fp8_act_quant = kernel_module.fp8_act_quant
|
| 16 |
+
|
| 17 |
+
fp8_act_quant(...)
|
| 18 |
+
```
|
| 19 |
+
|
| 20 |
+
## Available functions
|
| 21 |
+
- `fp8_act_quant`
|
| 22 |
+
- `matmul_2d`
|
| 23 |
+
- `matmul_batched`
|
| 24 |
+
- `matmul_grouped`
|
| 25 |
+
- `moe_fused_batched`
|
| 26 |
+
- `moe_fused_grouped`
|
| 27 |
+
|
| 28 |
+
## Benchmarks
|
| 29 |
+
|
| 30 |
+
No benchmark available yet.
|