8a2f72f18e
Pre-registers the E4 experiment that tests whether KVC + D→P RDMA snapshot push beats the naive PD-disagg E1 baseline on the inferact_50sess subset. Compared to E3 the only changed flag is --enable-d-to-p-sync. Three hypotheses (see docs/E4_PROTOCOL_ZH.md §2.3): H1 (main): E4 TTFT p99 ≤ E1 TTFT p99 H2: E4 reseed-mode TTFT < E3 reseed-mode TTFT H3: E4 success count ≥ E3 success count The full reseed → snapshot-push orchestration is wired inb9b0cf0(_attempt_d_to_p_sync); the SGLang scheduler RPCs and the runtime mem-leak fix are in86412bb/a369722.
83 lines
2.8 KiB
Bash
Executable File
83 lines
2.8 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# E4 — KVC v2 + RDMA + load-floor bonus + D→P snapshot push
|
|
#
|
|
# Identical to scripts/sweep_e3_kvc_v2_loadfloor_rdma.sh except for the
|
|
# additional --enable-d-to-p-sync flag (which causes agentic to orchestrate
|
|
# the snapshot RPCs on the reseed slow path, and stack.py to set
|
|
# SGLANG_SNAPSHOT_LINK_ENABLE=1 per worker).
|
|
#
|
|
# See docs/E4_PROTOCOL_ZH.md for hypothesis matrix.
|
|
|
|
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=${OUTPUT:-outputs/e4_kvc_v2_d_to_p_sync_50sess}
|
|
IB_DEVICE=${IB_DEVICE:-mlx5_60}
|
|
LOAD_FLOOR_BONUS=${LOAD_FLOOR_BONUS:-200}
|
|
|
|
if [ ! -f "$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 "=== E4: KVC v2 + RDMA + load-floor K=$LOAD_FLOOR_BONUS + D→P sync ==="
|
|
log "MODEL=$MODEL"
|
|
log "TRACE=$TRACE ($(wc -l < $TRACE) requests)"
|
|
log "OUTPUT=$OUTPUT"
|
|
log "IB_DEVICE=$IB_DEVICE"
|
|
log "MC_TRANSFER_TIMEOUT=${MC_TRANSFER_TIMEOUT:-default-30s}"
|
|
|
|
label=e4_kvc_v2_d_to_p_sync_run1
|
|
log ""
|
|
log "=== [E4] $label starting ==="
|
|
|
|
uv run --no-sync python -m agentic_pd_hybrid.cli benchmark-live \
|
|
--trace "$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 "$IB_DEVICE" \
|
|
--gpu-budget 4 \
|
|
--time-scale 1 \
|
|
--session-sample-rate 1.0 \
|
|
--target-duration-s 100000 \
|
|
--concurrency-limit 32 \
|
|
--timeout-s 1800 \
|
|
--request-timeout-s 300 \
|
|
--kvcache-admission-mode worker \
|
|
--kvcache-seed-min-turn-id 1 \
|
|
--kvcache-seed-max-inflight-decode -1 \
|
|
--kvcache-prefill-backup-policy release-after-transfer \
|
|
--kvcache-prefill-priority-eviction \
|
|
--kvcache-migration-reject-threshold 3 \
|
|
--kvcache-direct-max-uncached-tokens 8192 \
|
|
--kvcache-load-floor-bonus "$LOAD_FLOOR_BONUS" \
|
|
--enable-d-to-p-sync 2>&1 | tee -a "$LOG"
|
|
|
|
run_dir=$(ls -td "$OUTPUT"/kvcache-centric-*/ 2>/dev/null | head -1)
|
|
log "=== [E4] $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
|