For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Python module
max.pipelines.kv_cache.paged_kv_cache
Cache managersโ
LittleKVCacheBlock | One cache's page: block bid of cache cache_id. |
|---|---|
ScratchKVGroupCoordinator | A group holding one never-published block per request. |
Errorsโ
InsufficientBlocksError | Exception raised when there are insufficient free blocks to satisfy an allocation. |
|---|
Typesโ
KVHashAlgo | Supported hash algorithms for KV-cache block identity. |
|---|