mirror of
https://github.com/hanzoai/engine.git
synced 2026-11-20 14:17:52 +00:00
Prefix blocks were hashed from token content alone, so any two requests with the same prefix shared KV across orgs, and the sequence-level cache and its disk spill were keyed by tokens too. Every block hash, sequence-cache key and recurrent-prefix key now carries the request's cache salt, which the server derives from the gateway's X-Org-Id plus an optional cache_salt body field. Salted prefixes are dropped instead of spilled to disk. The scheduler also cached blocks no forward had written: a prompt preempted in the pass that admitted it, the last sampled token's slot of every finished or preempted sequence, and sequences that ended in error. Now only written positions become reusable. kv_isolation drives the real scheduler against a simulated KV store and checks every read for unwritten, foreign-context or other-tenant KV; hanzo.yml gates on it. Co-authored-by: Claude Opus 5.5 <[email protected]>
hanzo Python SDK
hanzo is the Python SDK for hanzo, a blazing-fast LLM inference engine.
Documentation
For full documentation, see:
Quick Install
pip install hanzo-cuda # NVIDIA GPUs
pip install hanzo-metal # Apple Silicon
pip install hanzo # CPU only