Update README.md
Browse files
README.md
CHANGED
|
@@ -30,6 +30,20 @@ default_stage:
|
|
| 30 |
bypass_divisibility_checks: false
|
| 31 |
```
|
| 32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
---
|
| 34 |
|
| 35 |
<div align="center">
|
|
|
|
| 30 |
bypass_divisibility_checks: false
|
| 31 |
```
|
| 32 |
|
| 33 |
+
## **Quick Start with vLLM**
|
| 34 |
+
|
| 35 |
+
Install vLLM:
|
| 36 |
+
|
| 37 |
+
```bash
|
| 38 |
+
pip install vllm
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
Serve your model:
|
| 42 |
+
|
| 43 |
+
```bash
|
| 44 |
+
vllm serve "prithivMLmods/gemma-4-31B-it-FP8"
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
---
|
| 48 |
|
| 49 |
<div align="center">
|