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

[Core] Deprecate xformers (#29262)

Browse Source 
Signed-off-by: Roger Wang <hey@rogerw.io>
This commit is contained in:
Roger Wang
2025-11-23 20:18:55 -08:00
committed by GitHub
parent 5253f4276f
commit 0ff70821c9
31 changed files with 77 additions and 963 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/kernels/attention/test_attention_selector.py
View File

@@ -34,7 +34,7 @@ DEVICE_MLA_BACKENDS = {
}
DEVICE_REGULAR_ATTN_BACKENDS = {
"cuda": ["XFORMERS", "FLASHINFER", "FLASH_ATTN"],
"cuda": ["FLASHINFER", "FLASH_ATTN"],
"hip": ["ROCM_ATTN"],
"cpu": ["CPU_ATTN"],
}
@@ -207,12 +207,6 @@ def test_env(
)
expected = "FLASHINFER"
assert backend.get_name() == expected
elif name == "XFORMERS":
backend = get_attn_backend(
32, torch.float16, None, block_size, use_mla=use_mla
)
expected = "XFORMERS"
assert backend.get_name() == expected
elif name == "FLASH_ATTN":
backend = get_attn_backend(
32, torch.float16, None, block_size, use_mla=use_mla