Update README.md
Browse files[BugFix] Fix compatibility issues with vLLM 0.10.1
README.md
CHANGED
|
@@ -18,7 +18,7 @@ Base model [Qwen/Qwen3-Coder-480B-A35B-Instruct](https://huggingface.co/Qwen/Qwe
|
|
| 18 |
|
| 19 |
|
| 20 |
### 【VLLM Launch Command for 8 GPUs (Single Node)】
|
| 21 |
-
<i
|
| 22 |
```
|
| 23 |
CONTEXT_LENGTH=32768 # 262144
|
| 24 |
|
|
@@ -46,6 +46,9 @@ vllm>=0.9.2
|
|
| 46 |
|
| 47 |
### 【Model Update History】
|
| 48 |
```
|
|
|
|
|
|
|
|
|
|
| 49 |
2025-08-11
|
| 50 |
1.Upload tokenizer_config.json
|
| 51 |
|
|
|
|
| 18 |
|
| 19 |
|
| 20 |
### 【VLLM Launch Command for 8 GPUs (Single Node)】
|
| 21 |
+
<i>Note: Note: When launching with 8 GPUs, --enable-expert-parallel must be specified; otherwise, the expert tensors cannot be evenly split across tensor parallel ranks. This option is not required for 4-GPU setups. </i>
|
| 22 |
```
|
| 23 |
CONTEXT_LENGTH=32768 # 262144
|
| 24 |
|
|
|
|
| 46 |
|
| 47 |
### 【Model Update History】
|
| 48 |
```
|
| 49 |
+
2025-08-19
|
| 50 |
+
1.[BugFix] Fix compatibility issues with vLLM 0.10.1
|
| 51 |
+
|
| 52 |
2025-08-11
|
| 53 |
1.Upload tokenizer_config.json
|
| 54 |
|