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:
Luis 🚀
2026-05-01 10:05:55 +08:00
committed by GitHub
co-authored by Andrew Sansom
parent 1adaa5056b
commit 14043dfecd
28 changed files with 2301 additions and 82 deletions
+2
View File
@@ -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(