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
+11
View File
@@ -125,6 +125,17 @@ class EmbedsPrompt(_PromptOptions):
prompt: NotRequired[str]
"""The prompt text corresponding to the token embeddings, if available."""
prompt_token_ids: NotRequired[list[int]]
"""Token IDs for mixed-mode inputs (chat completion with
`prompt_embeds` content parts). The tokens at positions where
`prompt_is_token_ids` is `False` are placeholder tokens that
get replaced by entries from `prompt_embeds` in the forward pass."""
prompt_is_token_ids: NotRequired[list[bool]]
"""Per-position mask, `True` uses the real token ID, `False` uses
the corresponding entry from `prompt_embeds`.
Must be the same length as `prompt_token_ids` when both are set."""
DecoderOnlyPrompt: TypeAlias = (
str | TextPrompt | list[int] | TokensPrompt | EmbedsPrompt