diff --git a/scripts/frank-default-large.env b/scripts/frank-default-large.env index 4a8c991..07dee93 100644 --- a/scripts/frank-default-large.env +++ b/scripts/frank-default-large.env @@ -39,7 +39,7 @@ CACHE_TYPE_V=q8_0 # ubatch is the compute-graph driver; larger ubatch = more VRAM, faster prefill. # Re-verified 2026-08-14 during the spec swap (see benchmark doc). BATCH_SIZE=8192 -UBATCH_SIZE=2048 +UBATCH_SIZE=4096 # Sampling settings — per HauhauCS Qwen3.6-27B model card. # Thinking-general: temp=1.0, top_p=0.95, top_k=20, min_p=0. # Clients may override per-request; these are the server-side defaults.