SyslogSolution/syslog-harness
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: heavy tier back to Dense→MoE→VLM (Dense now 98K)

Browse Source
This commit is contained in:
Abiba
2026-05-19 21:24:36 +00:00
parent 79965450bb
commit 32bd817e97
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
@@ -190,8 +190,8 @@ def route(rd, tier):
# TIER 3: Heavy reasoning — extremely large context or very long conversations # TIER 3: Heavy reasoning — extremely large context or very long conversations
if t > 50000 or turns > 25: if t > 50000 or turns > 25:
# Prefer models with larger context windows (MoE/VLM at 131K, Dense at 65K) # Dense first (98K, purpose-built for reasoning), then MoE/VLM 131K
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