Update README.md
Browse files
README.md
CHANGED
|
@@ -18,9 +18,8 @@ base_model_relation: quantized
|
|
| 18 |
|
| 19 |
### 【vLLM Single Node with 8 GPUs Startup Command】
|
| 20 |
<i>Note: You must use `--enable-expert-parallel` to start this model, otherwise the expert tensor TP will not divide evenly. This is required even for 2 GPUs.</i>
|
| 21 |
-
```
|
| 22 |
-
CONTEXT_LENGTH=32768
|
| 23 |
|
|
|
|
| 24 |
CONTEXT_LENGTH=32768
|
| 25 |
|
| 26 |
VLLM_USE_MODELSCOPE=true vllm serve \
|
|
|
|
| 18 |
|
| 19 |
### 【vLLM Single Node with 8 GPUs Startup Command】
|
| 20 |
<i>Note: You must use `--enable-expert-parallel` to start this model, otherwise the expert tensor TP will not divide evenly. This is required even for 2 GPUs.</i>
|
|
|
|
|
|
|
| 21 |
|
| 22 |
+
```
|
| 23 |
CONTEXT_LENGTH=32768
|
| 24 |
|
| 25 |
VLLM_USE_MODELSCOPE=true vllm serve \
|