mirror of
https://github.com/lukaszraczylo/llm-testbench.git
synced 2026-10-12 00:45:19 +00:00
Six qwen3.8-27b-uncensored requests in the 2026-08-30 run failed instantly with zero tokens while the replica was warming; the gateway reported them in-band and the client gave up on the first attempt. Both shapes now retry within the existing backoff budget.