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

[V1] V1 Enablement Oracle (#13726)

Browse Source 
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
This commit is contained in:
Robert Shaw
2025-03-15 01:02:20 -04:00
committed by GitHub
parent 8c0d15d5c5
commit d4d93db2c5
96 changed files with 1537 additions and 512 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/kernels/test_rocm_attention_selector.py
View File

@@ -24,7 +24,8 @@ def test_selector(monkeypatch):
with patch("vllm.attention.selector.current_platform", RocmPlatform()):
backend = get_attn_backend(16, torch.float16, torch.float16, 16, False)
assert backend.get_name() == "ROCM_FLASH"
assert (backend.get_name() == "ROCM_FLASH"
or backend.get_name() == "ROCM_ATTN_VLLM_V1")
# mla test for deepseek related
backend = get_attn_backend(576, torch.bfloat16, "auto", 16, False,
False, True)