Update README.md
Browse files
README.md
CHANGED
@@ -5,6 +5,8 @@ tags:
|
|
5 |
|
6 |
# Qwen2-72B-Instruct-FP8
|
7 |
|
|
|
|
|
8 |
Quantized with [AutoFP8](https://github.com/neuralmagic/autofp8) using the following script on 8xA100:
|
9 |
|
10 |
```python
|
|
|
5 |
|
6 |
# Qwen2-72B-Instruct-FP8
|
7 |
|
8 |
+
Ready to use with `vllm>=0.4.3`.
|
9 |
+
|
10 |
Quantized with [AutoFP8](https://github.com/neuralmagic/autofp8) using the following script on 8xA100:
|
11 |
|
12 |
```python
|