fanjiang98 commited on
Commit
a85af58
·
verified ·
1 Parent(s): 3793a62

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -183,6 +183,8 @@ outputs = model.generate(inputs, max_new_tokens=256)
183
  print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
184
  ```
185
 
 
 
186
  ## Citation
187
 
188
  ```bibtex
 
183
  print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
184
  ```
185
 
186
+ **Note**: vLLM is the recommended engine for deployment, as SGLang currently lacks support for MoE models with tied embeddings (see [PR #20127](https://github.com/sgl-project/sglang/pull/20127)). If SGLang is required for your workflow, please use the specific build at commit e5f48b32abff027d859a43b7d5ba3aece04471c7.
187
+
188
  ## Citation
189
 
190
  ```bibtex