fix: heavy tier — Dense first (best for reasoning), then MoE, then VLM

This commit is contained in:
Abiba
2026-05-19 18:20:20 +00:00
parent 15c474aea0
commit 7a78c0f98d
+1 -1
View File
@@ -183,7 +183,7 @@ def route(rd, tier):
# TIER 3: Heavy reasoning — large context or very long conversations # TIER 3: Heavy reasoning — large context or very long conversations
if t > 4000 or turns > 8: if t > 4000 or turns > 8:
candidates = [m for m in ["qwen3.6-35B-A3B","qwen3.5-9b-vlm","qwen3.6-27B-code"] if m in avail] candidates = [m for m in ["qwen3.6-27B-code","qwen3.6-35B-A3B","qwen3.5-9b-vlm"] if m in avail]
result = select_best_gpu(candidates, "heavy_reasoning") result = select_best_gpu(candidates, "heavy_reasoning")
if result: return result if result: return result