diff --git a/scripts/frank-medium.env b/scripts/frank-medium.env index 0d57c31..fbc64c5 100644 --- a/scripts/frank-medium.env +++ b/scripts/frank-medium.env @@ -129,7 +129,10 @@ THREAD_BATCH=8 # f16 K/V: an agentic checkpoint is the wrong place to spend KV precision. CACHE_TYPE_K=f16 CACHE_TYPE_V=f16 -CTX_CHECKPOINTS=8 +# Context checkpoints: 0 is the build's default -- no per-slot KV snapshots, so +# a re-sent or rewound conversation re-prefills instead of rewinding. Stated +# explicitly so the tunable stays visible rather than merely absent. +CTX_CHECKPOINTS=0 CACHE_RAM=8192 # Sampling defaults for requests that send none -- the values the vLLM