[3/N][KV-Cache Layout Refactor] Standardize Mamba cache; drop get_transfer_cache_regions (#44456)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
co-authored by
Claude
OpenAI Codex
parent
eb44b3aaa4
commit
6700813f86
@@ -125,8 +125,7 @@ def test_register_kv_caches(backend):
|
||||
own dedicated tensors.
|
||||
|
||||
Uses the real GPUModelRunner.initialize_kv_cache_tensors to produce
|
||||
kv_caches, which automatically applies
|
||||
_update_hybrid_attention_mamba_layout for hybrid models.
|
||||
the raw per-layer kv_caches registered by the connector.
|
||||
|
||||
Verifies that the canonicalized CanonicalKVCaches has the correct
|
||||
block tensors, tensor_idx references, and page sizes across all groups.
|
||||
|
||||
Reference in New Issue
Block a user