diff --git a/hw/dixie/default.nix b/hw/dixie/default.nix index a82736b..1bc6367 100644 --- a/hw/dixie/default.nix +++ b/hw/dixie/default.nix @@ -41,10 +41,11 @@ let [ornith-1.5-9b-uncensored] model = ${modelsDir}/ornith-1.5-9b-uncensored/Ornith-1.5-9B-uncensored.Q4_K_M.gguf ; serves the deriver, all dialectic levels and three agents' approval guardians at once: - ; 6 slots over one 64k pool (at 2 x 16k, concurrent deriver + dialectic hit "failed to find + ; 8 slots over one 96k pool so tiny guardian/title calls still find a slot while Honcho + ; catch-up (deriver + dreams + dialectic) holds 6 (at 2 x 16k, concurrent calls hit "failed to find ; free space in the KV cache" and stalled) - ctx-size = 65536 - parallel = 6 + ctx-size = 98304 + parallel = 8 ; Runaway guard carried over from straylight: helper tasks need short answers. reasoning-budget = 2048 n-predict = 4096