[Attention] Refactor CUDA attention backend selection logic (#24794)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Matthew Bonanni
2025-11-11 07:40:44 -05:00
committed by GitHub
co-authored by Luka Govedič
parent 2e78150d24
commit b30dfa03c5
61 changed files with 1338 additions and 1002 deletions
+9 -1
View File
@@ -21,7 +21,15 @@ else:
logger = init_logger(__name__)
BlockSize = Literal[1, 8, 16, 32, 64, 128, 256]
CacheDType = Literal["auto", "bfloat16", "fp8", "fp8_e4m3", "fp8_e5m2", "fp8_inc"]
CacheDType = Literal[
"auto",
"bfloat16",
"fp8",
"fp8_e4m3",
"fp8_e5m2",
"fp8_inc",
"fp8_ds_mla",
]
MambaDType = Literal["auto", "float32"]
PrefixCachingHashAlgo = Literal["sha256", "sha256_cbor"]
KVOffloadingBackend = Literal["native", "lmcache"]