[KV Connector][Mooncake] Add cache_prefix to namespace store keys (#45767)

Signed-off-by: Dao Le <Dao007forever@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Dao007forever
2026-06-16 10:24:20 -07:00
committed by GitHub
co-authored by Claude Opus 4.8
parent 188c68798e
commit 44b2512767
4 changed files with 43 additions and 0 deletions
@@ -205,6 +205,7 @@ the vLLM JSON config.
- `load_async` (bool): Enable asynchronous loading for better compute-I/O overlap. Default: `true`.
- `enable_cross_layers_blocks` (bool): Enable cross-layer block packing for reduced store operations. Default: `false`.
- `lookup_rpc_port` (int): Custom port for the ZMQ lookup RPC socket. Default: `0`.
- `cache_prefix` (str): Namespace prepended to every store key. Lets separate deployments share one Mooncake master without polluting each other — instances configured with different prefixes never see each other's cached blocks, even for identical prompts. All instances that should share a prefix cache must use the same value. Default: `""` (no prefix; keys are byte-identical to the unprefixed format).
## Notes