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

7
tests/v1/spec_decode/test_max_len.py
View File

@@ -41,12 +41,11 @@ def test_eagle_max_len(monkeypatch: pytest.MonkeyPatch,
m.setenv("VLLM_USE_V1", "1")
m.setenv("VLLM_ATTENTION_BACKEND", attn_backend)
if (attn_backend == "TRITON_ATTN_VLLM_V1"
and not current_platform.is_rocm()):
pytest.skip("TRITON_ATTN_VLLM_V1 does not support "
if (attn_backend == "TRITON_ATTN" and not current_platform.is_rocm()):
pytest.skip("TRITON_ATTN does not support "
"multi-token eagle spec decode on current platform")
if attn_backend == "FLASH_ATTN_VLLM_V1" and current_platform.is_rocm():
if attn_backend == "FLASH_ATTN" and current_platform.is_rocm():
m.setenv("VLLM_ROCM_USE_AITER", "1")
llm = LLM(