Extend renderer with embedding support and integrate completion endpoint (#24405)

Signed-off-by: sfeng33 <4florafeng@gmail.com>
2025-09-09 10:46:46 -07:00
parent 9ad0688e43
commit 15cb047e25
9 changed files with 410 additions and 309 deletions
--- a/vllm/inputs/data.py
+++ b/vllm/inputs/data.py
@@ -52,6 +52,9 @@ class TokensPrompt(TypedDict):
    prompt_token_ids: list[int]
    """A list of token IDs to pass to the model."""

+    prompt: NotRequired[str]
+    """The prompt text corresponding to the token IDs, if available."""
+
    token_type_ids: NotRequired[list[int]]
    """A list of token type IDs to pass to the cross encoder model."""