[Model] Pipeline parallel support for Mixtral (#6516)

2024-07-17 19:26:04 -07:00
parent b5241e41d9
commit b5af8c223c
3 changed files with 60 additions and 19 deletions
--- a/vllm/config.py
+++ b/vllm/config.py
@@ -34,6 +34,7 @@ _PP_SUPPORTED_MODELS = [
    "MistralForCausalLM",
    "Phi3ForCausalLM",
    "GPT2LMHeadModel",
+    "MixtralForCausalLM",
 ]