← older: fast__qwen3.5-122b-a10b__20260712-141049all runs · task boardnewer: fast__qwen3.5-122b-a10b__20260712-144656

fast__qwen3.5-122b-a10b__20260712-143738

122b fast run part 2/3 — resume batch after memory abort: nginx PASS, openssl PASS, cancel-async FAIL

Continuation of the aborted fast__qwen3.5-122b-a10b__20260712-141049 (see its NOTES for the llama-server RAM-ratchet story). llama-swap restarted immediately before this batch (fresh 59 GiB available); same MinimalPi + scaled cap map.

Ratchet datapoint: this 8m37s batch alone burned 59 GiB → 299 MiB MemAvailable, confirming the burn is proportional to inference activity and that per-batch llama-swap restarts are load-bearing for 122b benchmark runs.

Run details

modelllama-local/qwen3.5-122b-a10bagentharnesses.minimal_pi:MinimalPithinkingonreasoning budgetdirect (server/none)* — see journal for the authoritative mechanismmaxTokens / contextWindow65536 / 196608agent timeout ×2.0trials3 of 3 — 2 pass · 1 failmean reward0.67tokens (job total)118,592 in / 8,447 outstarted / finished2026-07-12T14:37 / 2026-07-12T14:46wall clock8m37s

Tasks

cancel-async-tasks — 0/1 passed

#resulttotalagentin/out tokflags
1FAIL3m05s2m18s18847/2265
🔍 view

nginx-request-logging — 1/1 passed

#resulttotalagentin/out tokflags
1PASS2m03s1m27s41906/2012
🔍 view

openssl-selfsigned-cert — 1/1 passed

#resulttotalagentin/out tokflags
1PASS3m28s2m53s57839/4170
🔍 view