feat(experiments): E4-pressured points at third_party/traces SWE-Bench trace

Switches the default --trace from outputs/inferact_50sess.jsonl
(median 63K, p99 143K, 1285 reqs) to
third_party/traces/qwen35-swebench-50sess.jsonl (median 27K,
p99 92K, 4449 reqs across 52 sessions). Smaller per-request
inputs let us check whether the queue-induced TTFT collapse
the user flagged is workload-specific. Total trace is 3.5x
larger so the run will cover more turns per session.
This commit is contained in:
Claude Code Agent
2026-05-13 14:19:25 +08:00
parent 2dfe22ab20
commit a953346a0c

View File

@@ -26,7 +26,7 @@ if [ -z "${CUDA_HOME:-}" ]; then
fi
MODEL=${MODEL:-/mnt/models/Qwen/Qwen3-30B-A3B-Instruct-2507}
TRACE=${TRACE:-outputs/inferact_50sess.jsonl}
TRACE=${TRACE:-third_party/traces/qwen35-swebench-50sess.jsonl}
OUTPUT=${OUTPUT:-outputs/e4p_kvc_v2_d_to_p_sync_pressured_50sess}
IB_DEVICE=${IB_DEVICE:-mlx5_60}
LOAD_FLOOR_BONUS=${LOAD_FLOOR_BONUS:-200}