[Frontend] Split the offline inference APIs and utils. (#43553)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2026-05-26 05:20:24 +00:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent f815c99954
commit d5cf7b4a2c
5 changed files with 642 additions and 713 deletions
@@ -192,7 +192,7 @@ def test_preprocess_cmpl_applies_mm_processor_kwargs_to_renderer(
llm.renderer = renderer
monkeypatch.setattr(
"vllm.entrypoints.llm.parse_model_prompt",
"vllm.entrypoints.offline_utils.parse_model_prompt",
lambda _model_config, parsed_prompt: parsed_prompt,
)
@@ -226,7 +226,7 @@ def test_preprocess_cmpl_keeps_prompt_mm_processor_kwargs_when_no_override(
llm.renderer = renderer
monkeypatch.setattr(
"vllm.entrypoints.llm.parse_model_prompt",
"vllm.entrypoints.offline_utils.parse_model_prompt",
lambda _model_config, parsed_prompt: parsed_prompt,
)