feat: Enable prompt_embeds Content Part Support in vLLM Chat Completions API (#40720)
Signed-off-by: Luis Robaina <luis@protopia.ai> Signed-off-by: Luis Robaina 🚀 <luisfabian1545@gmail.com> Signed-off-by: LuisRobaina <luis@protopia.ai> Co-authored-by: Andrew Sansom <qthequartermasterman@gmail.com>
This commit is contained in:
@@ -769,6 +769,8 @@ class BaseRenderer(ABC, Generic[_T]):
|
||||
return embeds_input(
|
||||
prompt_embeds=prompt_embeds,
|
||||
cache_salt=prompt.get("cache_salt"),
|
||||
prompt_token_ids=prompt.get("prompt_token_ids"),
|
||||
is_token_ids=prompt.get("prompt_is_token_ids"),
|
||||
)
|
||||
|
||||
async def _process_tokens_async(
|
||||
|
||||
Reference in New Issue
Block a user