Update README.md
Browse files
README.md
CHANGED
|
@@ -124,6 +124,9 @@ output = model.generate_from_batch(
|
|
| 124 |
|
| 125 |
Note that this can sometimes change the output of the model compared to running with float32 weights.
|
| 126 |
|
|
|
|
|
|
|
|
|
|
| 127 |
|
| 128 |
## Evaluations
|
| 129 |
|
|
|
|
| 124 |
|
| 125 |
Note that this can sometimes change the output of the model compared to running with float32 weights.
|
| 126 |
|
| 127 |
+
## vLLM
|
| 128 |
+
Molmo is supported in vLLM, however please use version <=0.7.2 until a [prepreprocessing bug](https://github.com/vllm-project/vllm/issues/26451) is fixed.
|
| 129 |
+
|
| 130 |
|
| 131 |
## Evaluations
|
| 132 |
|