Feature/vllm/input embedding completion api (#17590)

Signed-off-by: Andrew Sansom <andrew@protopia.ai>
Signed-off-by: Nan2018 <nan@protopia.ai>
Co-authored-by: 临景 <linjing.yx@alibaba-inc.com>
Co-authored-by: Bryce1010 <bryceyx@gmail.com>
Co-authored-by: Andrew Sansom <andrew@protopia.ai>
Co-authored-by: Andrew Sansom <qthequartermasterman@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

vllm/entrypoints/logger.py

@@ -2,6 +2,8 @@
 
 from typing import Optional, Union
 
+import torch
+
 from vllm.logger import init_logger
 from vllm.lora.request import LoRARequest
 from vllm.pooling_params import PoolingParams
@@ -23,6 +25,7 @@ class RequestLogger:
         request_id: str,
         prompt: Optional[str],
         prompt_token_ids: Optional[list[int]],
+        prompt_embeds: Optional[torch.Tensor],
         params: Optional[Union[SamplingParams, PoolingParams,
                                BeamSearchParams]],
         lora_request: Optional[LoRARequest],
@@ -39,6 +42,8 @@ class RequestLogger:
         logger.info(
             "Received request %s: prompt: %r, "
             "params: %s, prompt_token_ids: %s, "
+            "prompt_embeds shape: %s, "
             "lora_request: %s, prompt_adapter_request: %s.", request_id,
-            prompt, params, prompt_token_ids, lora_request,
-            prompt_adapter_request)
+            prompt, params, prompt_token_ids,
+            prompt_embeds.shape if prompt_embeds is not None else None,
+            lora_request, prompt_adapter_request)