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:
@@ -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
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user