[Model] Support DeepSeek-V4.1-Flash (#56214)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com> Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai> Signed-off-by: andyluo7 <andy.luo@amd.com> Signed-off-by: zjy0516 <riverclouds.zhu@qq.com> Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai> Co-authored-by: andyluo7 <andy.luo@amd.com> Co-authored-by: OpenAI Codex <codex@openai.com> Co-authored-by: zjy0516 <riverclouds.zhu@qq.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Jee Jee Li
andyluo7
OpenAI Codex
zjy0516
Claude Opus 5
parent
e6821ceac9
commit
e77daef89e
@@ -616,6 +616,8 @@ def test_dummy_maverick(
|
||||
) -> None:
|
||||
# Disable multiprocessing allows us to access model executor from LLM engine
|
||||
monkeypatch.setenv("VLLM_ENABLE_V1_MULTIPROCESSING", "0")
|
||||
# The forked test process may inherit CUDA state from test collection.
|
||||
monkeypatch.setenv("VLLM_WORKER_MULTIPROC_METHOD", "spawn")
|
||||
|
||||
model_path = create_reduced_maverick_model(
|
||||
original_model_name=original_model_name,
|
||||
|
||||
Reference in New Issue
Block a user