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
+6
View File
@@ -94,6 +94,12 @@ class EngineCoreRequest(
data_parallel_rank: int | None
prompt_embeds: torch.Tensor | None = None
# Per-position mask for mixed-mode inputs (e.g chat completion with
# prompt_embeds content parts). `True` means the position is a real
# token ID; `False` means the position uses a pre-computed entry from
# `prompt_embeds`. `None` for pure-tokens and pure-embeds requests.
prompt_is_token_ids: list[bool] | None = None
# Index of the client, used to ensure outputs are sent back to the same
# client for this request when scaling out the front-end.
client_index: int = 0