abiba-bot/inference-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: raise heavy threshold — 4000→12000 tokens, 8→15 turns

Browse Source
This commit is contained in:
Abiba
2026-05-19 20:10:07 +00:00
parent 5971ceee4e
commit e90bf0216d
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
router/router.py
+2 -2
View File
@@ -181,8 +181,8 @@ def route(rd, tier):
if "qwen3.6-27B-code" in avail and not is_gpu_busy("qwen3.6-27B-code"): if "qwen3.6-27B-code" in avail and not is_gpu_busy("qwen3.6-27B-code"):
return {"model":"qwen3.6-27B-code","reason":"simple_conv_fallback"} return {"model":"qwen3.6-27B-code","reason":"simple_conv_fallback"}
# TIER 3: Heavy reasoning — large context or very long conversations # TIER 3: Heavy reasoning — very large context or very long conversations
if t > 4000 or turns > 8: if t > 12000 or turns > 15:
candidates = [m for m in ["qwen3.6-27B-code","qwen3.6-35B-A3B","qwen3.5-9b-vlm"] 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