[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
This commit is contained in:
@@ -294,6 +294,7 @@ class TestTurboQuantKVCacheSpec:
|
||||
head_size_v=128,
|
||||
num_kv_heads=4,
|
||||
sliding_window=None,
|
||||
get_attn_backend=lambda: TurboQuantAttentionBackend,
|
||||
)
|
||||
vllm_config = SimpleNamespace(cache_config=SimpleNamespace(block_size=32))
|
||||
|
||||
|
||||
Reference in New Issue
Block a user