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
+4 -1
View File
@@ -541,7 +541,10 @@ class OpenAIServingRender:
default_template_kwargs,
dict(
tools=tool_dicts,
tokenize=is_mistral_tokenizer(renderer.tokenizer),
tokenize=(
is_mistral_tokenizer(renderer.tokenizer)
or self.model_config.enable_prompt_embeds
),
),
)