diff --git a/router/router.py b/router/router.py index 5af41d8..de0d340 100644 --- a/router/router.py +++ b/router/router.py @@ -218,8 +218,8 @@ def route(rd, tier): result = select_best_gpu(fallback, "lightweight_fallback") if result: return result - # TIER 2: Simple conversations — short context, any prompt → VLM first, Dense second - if t <= 4000 and turns <= 6 and "qwen3.5-9b-vlm" in avail: + # TIER 2: Simple conversations — VLM primary (up to 10K tok), any prompt → VLM first, Dense second + if t <= 10000 and turns <= 10 and "qwen3.5-9b-vlm" in avail: if not is_gpu_busy("qwen3.5-9b-vlm"): return {"model":"qwen3.5-9b-vlm","reason":"simple_conv"} # VLM busy — fall back to Dense, then MoE