[Bugfix][Attention] Explicitly report support for kv_cache_dtype bfloat16 (#32795)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-01-22 14:05:18 -05:00
committed by GitHub
parent 744ef30484
commit 955b43a5a5
13 changed files with 31 additions and 11 deletions

View File

@@ -259,6 +259,7 @@ class TritonAttentionBackend(AttentionBackend):
]
supported_kv_cache_dtypes: ClassVar[list[CacheDType]] = [
"auto",
"bfloat16",
"fp8",
"fp8_e4m3",
"fp8_e5m2",