#!/bin/bash # Smoke test: pd-disaggregation with mooncake TCP, 100 requests set -euo pipefail cd "$(dirname "$0")/.." # Sample a small trace for smoke testing uv run agentic-pd-hybrid sample-sessions \ --trace outputs/qwen35-swebench-500.jsonl \ --output outputs/qwen35-smoke-3sess.jsonl \ --session-sample-rate 0.02 \ --min-turns 5 \ --target-duration-s 300 \ --max-requests 100 # Run smoke test uv run agentic-pd-hybrid benchmark-live \ --trace outputs/qwen35-smoke-3sess.jsonl \ --output-root outputs/smoke \ --mechanism pd-disaggregation \ --policy default \ --model-path /mnt/kzlin/workflow/pd-hybrid/simm-swe-bench/models/Qwen3.5-35B-A3B \ --prefill-workers 1 --decode-workers 1 \ --prefill-tp-size 4 --decode-tp-size 4 \ --prefill-gpu-ids 0,1,2,3 --decode-gpu-ids 4,5,6,7 \ --transfer-backend mooncake \ --gpu-budget 8 \ --time-scale 10 \ --concurrency-limit 32 \ --timeout-s 900 \ --request-timeout-s 300