biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V0 deprecation] Remove _VLLM_V1 suffixes from attention backend names (#25489)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
This commit is contained in:
Matthew Bonanni
2025-09-25 13:37:50 -04:00
committed by GitHub
parent 71b25b0d48
commit 3468f17ebe
42 changed files with 131 additions and 174 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/entrypoints/openai/test_serving_chat.py
View File

@@ -68,7 +68,7 @@ def default_server_args(with_tool_parser: bool):
def gptoss_server(monkeypatch_module: pytest.MonkeyPatch,
default_server_args: list[str]):
with monkeypatch_module.context() as m:
m.setenv("VLLM_ATTENTION_BACKEND", "TRITON_ATTN_VLLM_V1")
m.setenv("VLLM_ATTENTION_BACKEND", "TRITON_ATTN")
with RemoteOpenAIServer(GPT_OSS_MODEL_NAME,
default_server_args) as remote_server:
yield remote_server