mstar.engine.resources.kv#
Modules
What a model declares about a KV cache: its shape, its spec, its step. |
|
Host-side page pool for KV cache offloading. |
|
Page keys for cross-request prefix reuse. |
|
The KV plan: what KVManager.plan hands its dependents. |
|
The prefix index: which cached page holds which key, and which to drop first. |
|
Ring KV storage: a fixed horizon of frame slots, overwritten in place. |
|
KV transfer: moving one request's pages between engines. |