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
@@ -11,7 +11,9 @@ from vllm import LLM, SamplingParams
def _make_mock_llm() -> LLM:
llm = object.__new__(LLM)
llm.model_config = SimpleNamespace(runner_type="generate")
llm.model_config = SimpleNamespace(
runner_type="generate", enable_prompt_embeds=False
)
return llm