[Model][Misc] Add e5-mistral-7b-instruct and Embedding API (#3734)

2024-05-11 11:30:37 -07:00
parent 4e12131089
commit e254497b66
38 changed files with 1627 additions and 160 deletions
--- a/vllm/engine/arg_utils.py
+++ b/vllm/engine/arg_utils.py
@@ -574,6 +574,7 @@ class EngineArgs:
                                 speculative_config.num_lookahead_slots),
            delay_factor=self.scheduler_delay_factor,
            enable_chunked_prefill=self.enable_chunked_prefill,
+            embedding_mode=model_config.embedding_mode,
        )
        lora_config = LoRAConfig(
            max_lora_rank=self.max_lora_rank,