frank-medium: checkpoints back to the build's default (0)

Step 2 of the operator's six. --ctx-checkpoints 8 held per-slot KV snapshots; 0 is what llama.cpp ships, and the fleet's clients open conversations fresh.
2026-09-16 19:51:06 -07:00
parent b6d4914fcc
commit 169eba0734
1 changed files with 4 additions and 1 deletions
@@ -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