feat(experiments): E2 sweep — KVC v2 + RDMA on the matched subset

KVC v2 config from sweep_ts1_migration_v2.sh (reset-on-success +
direct-append threshold 8192) layered on top of the RDMA-enabled
mooncake stack, against the same outputs/inferact_50sess.jsonl
subset that E1 uses. Pair-wise contrast tests H1 (KVC layer marginal
contribution on top of 1P3D + kv-aware) and H2/H3 (RDMA reducing
reseed slow-path tail).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

scripts/sweep_e2_kvc_v2_rdma.sh

@@ -0,0 +1,90 @@
+#!/usr/bin/env bash
+# E2 — KVC v2 + RDMA, ts=1
+#
+# Tests hypotheses H2/H3 from ONBOARDING_NEXT_AGENT_ZH §3.1: validate
+# that enabling real RDMA pushes TTFT p99 from the reported 1.28s
+# (TCP loopback) down toward ~0.7s (still expected to lose to DP 0.43s
+# because re-prefill segment of reseed slow-path remains).
+#
+# Mechanism = kvcache-centric; policy = kv-aware; topology = 1P3D.
+# All --kvcache-* tuning flags from sweep_ts1_migration_v2.sh
+# (reset-on-success + threshold 8192). RDMA on (mlx5_60).
+#
+# Uses the same outputs/inferact_50sess.jsonl as E1 — see
+# scripts/sample_trace_subset.py — so the two runs are paired.
+#
+# Prerequisites:
+#   - source scripts/setup_env.sh
+#   - E1 must already have completed (releases GPUs)
+#
+# Usage:
+#   bash scripts/sweep_e2_kvc_v2_rdma.sh
+
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+if [ -z "${CUDA_HOME:-}" ]; then
+  echo "ERROR: CUDA_HOME not set. Source scripts/setup_env.sh first." >&2
+  exit 1
+fi
+
+MODEL=${MODEL:-/mnt/models/Qwen/Qwen3-30B-A3B-Instruct-2507}
+TRACE=${TRACE:-outputs/inferact_50sess.jsonl}
+OUTPUT=${OUTPUT:-outputs/e2_kvc_v2_rdma_50sess}
+IB_DEVICE=${IB_DEVICE:-mlx5_60}
+
+if [ ! -f "$TRACE" ]; then
+  echo "ERROR: trace not found at $TRACE" >&2
+  echo "Run: uv run --no-sync python scripts/sample_trace_subset.py --output $TRACE --sessions 50" >&2
+  exit 1
+fi
+
+mkdir -p "$OUTPUT"
+LOG="$OUTPUT/sweep.log"
+
+log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*" | tee -a "$LOG"; }
+
+log "=== E2: KVC v2 + RDMA, ts=1 ==="
+log "MODEL=$MODEL"
+log "TRACE=$TRACE ($(wc -l < $TRACE) requests)"
+log "OUTPUT=$OUTPUT"
+log "IB_DEVICE=$IB_DEVICE"
+
+label=e2_kvc_v2_rdma_run1
+log ""
+log "=== [E2] $label starting ==="
+
+uv run --no-sync python -m agentic_pd_hybrid.cli benchmark-live \
+  --trace "$TRACE" \
+  --output-root "$OUTPUT" \
+  --mechanism kvcache-centric \
+  --policy kv-aware \
+  --model-path "$MODEL" \
+  --prefill-workers 1 --decode-workers 3 \
+  --prefill-tp-size 1 --decode-tp-size 1 \
+  --prefill-gpu-ids 0 --decode-gpu-ids 1,2,3 \
+  --transfer-backend mooncake \
+  --force-rdma --ib-device "$IB_DEVICE" \
+  --gpu-budget 4 \
+  --time-scale 1 \
+  --session-sample-rate 1.0 \
+  --target-duration-s 100000 \
+  --concurrency-limit 32 \
+  --timeout-s 1800 \
+  --request-timeout-s 300 \
+  --kvcache-admission-mode worker \
+  --kvcache-seed-min-turn-id 1 \
+  --kvcache-seed-max-inflight-decode -1 \
+  --kvcache-prefill-backup-policy release-after-transfer \
+  --kvcache-prefill-priority-eviction \
+  --kvcache-migration-reject-threshold 3 \
+  --kvcache-direct-max-uncached-tokens 8192 2>&1 | tee -a "$LOG"
+
+run_dir=$(ls -td "$OUTPUT"/kvcache-centric-*/ 2>/dev/null | head -1)
+log "=== [E2] $label COMPLETED, artifacts at $run_dir ==="
+
+if [ -f "$run_dir/request-metrics.jsonl.summary.json" ]; then
+  cp "$run_dir/request-metrics.jsonl.summary.json" "$OUTPUT/${label}_summary.json"
+  cp "$run_dir/request-metrics.jsonl" "$OUTPUT/${label}_metrics.jsonl"
+  log "=== summary saved to $OUTPUT/${label}_summary.json ==="
+fi