[Models] Support Qwen model with PP (#6974)

Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
2024-08-01 12:40:43 -07:00
parent f4fd390f5d
commit fc912e0886
3 changed files with 46 additions and 11 deletions
--- a/vllm/config.py
+++ b/vllm/config.py
@@ -42,6 +42,7 @@ _PP_SUPPORTED_MODELS = [
    "NemotronForCausalLM",
    "Qwen2ForCausalLM",
    "Qwen2MoeForCausalLM",
+    "QWenLMHeadModel",
 ]