[2026-04-28 17:51:41] Starting TP1 v3 sweep (KVC with kv-aware policy) [2026-04-28 17:51:41] Model: /mnt/kzlin/workflow/pd-hybrid/simm-swe-bench/models/Qwen3-30B-A3B-Instruct-2507 [2026-04-28 17:51:41] Trace: outputs/qwen35-swebench-50sess.jsonl (4449 requests, 52 sessions) [2026-04-28 17:51:41] Key change: --policy kv-aware for KVC (was --policy default in v2) [2026-04-28 17:51:41] [2026-04-28 17:51:41] === [EXP1] 1P7D KVC kv-aware === [2026-04-28 18:43:43] === exp1_1p7d_kvc_kvaware COMPLETED === [2026-04-28 18:43:43] Summary: { "actual_output_tokens_stats": { "count": 4086.0, "mean": 213.95105237395987, "p50": 83.0, "p90": 562.0, "p99": 1346.0 }, "cache_hit_request_count": 3929, "cached_tokens_stats": { "count": 4449.0, "mean": 22635.924702180266, "p50": 20010.0, "p90": 48002.0, "p99": 65424.0 }, "decode_request_priorities": {}, "error_count": 363, "execution_modes": { "kvcache-centric": 363, "kvcache-direct-to-d-session": 1716, "pd-router-d-session-reseed": 23, "pd-router-fallback-d-backpressure": 12, "pd-router-fallback-large-append": 5, "pd-router-fallback-large-append-seed-filter-early-turn": 51, "pd-router-fallback-large-append-session-cap": 2148, "pd-router-fallback-no-d-capacity": 7, "pd-router-fallback-session-cap": 32, "pd-router-large-append-reseed": 39, "pd-router-large-append-reseed-after-eviction": 2, "pd-router-turn1-d-backpressure": 1, "pd-router-turn1-no-d-capacity": 3, "pd-router-turn1-seed": 34, "pd-router-turn1-session-cap": 13 }, "latency_stats_s": { "count": 4086.0, "mean": 4.8753733304192455, "p50": 1.754677688702941, "p90": 12.66968655679375, "p99": 28.717210091650486 }, "mechanisms": { "kvcache-centric": 4449 }, "per_decode_load": { "decode-0": 616, "decode-1": 658, "decode-2": 674, "decode-3": 582, "decode-4": 656, "decode-5": 662, "decode-6": 601 }, "per_prefill_load": { "prefill-0": 4449 }, "prefill_request_priorities": { "-100": 98, "100": 2272 }, "re_prefill_count": 0, "request_count": 4449, "reuse_expected_count": 4397, "reuse_observed_count": 4397, "router_url": "http://127.0.0.1:8000", "session_reset_count": 0, "session_reused_count": 1716, "total_actual_kv_transfer_blocks": 62123, "total_cached_tokens": 100707229, "total_kv_transfer_blocks": 105235, "tpot_stats_s": { "count": 4086.0, "mean": 0.005829451223571163, "p50": 0.005684156496173296, "p90": 0.007143743503740225, "p99": 0.008634991403068266 }, "trace_path": "outputs/qwen3-30b-tp1-v3-kvaware/kvcache-centric-kv-aware-worker-admission-20260428T095141Z/sampled-trace.jsonl", "truncated_request_count": 42, "ttft_stats_s": { "count": 4086.0, "mean": 3.5955862397812597, "p50": 0.36274072993546724, "p90": 10.972254231572151, "p99": 27.433656523004174 } } [2026-04-28 18:43:43] Saved to outputs/qwen3-30b-tp1-v3-kvaware/exp1_1p7d_kvc_kvaware_summary.json + exp1_1p7d_kvc_kvaware_metrics.jsonl [2026-04-28 18:43:43] [2026-04-28 18:43:43] === [EXP2] 2P6D KVC kv-aware === [2026-04-28 19:30:38] === exp2_2p6d_kvc_kvaware COMPLETED === [2026-04-28 19:30:38] Summary: { "actual_output_tokens_stats": { "count": 4440.0, "mean": 225.87972972972972, "p50": 86.0, "p90": 576.0, "p99": 1347.0 }, "cache_hit_request_count": 4201, "cached_tokens_stats": { "count": 4449.0, "mean": 24345.55787817487, "p50": 21504.0, "p90": 48792.0, "p99": 69120.0 }, "decode_request_priorities": {}, "error_count": 9, "execution_modes": { "kvcache-centric": 9, "kvcache-direct-to-d-session": 1358, "pd-router-d-session-reseed": 12, "pd-router-fallback-d-backpressure": 2, "pd-router-fallback-large-append-seed-filter-early-turn": 52, "pd-router-fallback-large-append-session-cap": 2902, "pd-router-fallback-session-cap": 25, "pd-router-large-append-reseed": 34, "pd-router-large-append-reseed-after-eviction": 4, "pd-router-turn1-d-backpressure": 1, "pd-router-turn1-seed": 30, "pd-router-turn1-session-cap": 20 }, "latency_stats_s": { "count": 4440.0, "mean": 3.582334662846558, "p50": 1.517257746309042, "p90": 9.225348330102861, "p99": 18.70269925892353 }, "mechanisms": { "kvcache-centric": 4449 }, "per_decode_load": { "decode-0": 710, "decode-1": 630, "decode-2": 763, "decode-3": 737, "decode-4": 879, "decode-5": 730 }, "per_prefill_load": { "prefill-0": 2225, "prefill-1": 2224 }, "prefill_request_priorities": { "-100": 80, "100": 3002 }, "re_prefill_count": 0, "request_count": 4449, "reuse_expected_count": 4397, "reuse_observed_count": 4397, "router_url": "http://127.0.0.1:8000", "session_reset_count": 0, "session_reused_count": 1358, "total_actual_kv_transfer_blocks": 78979, "total_cached_tokens": 108313387, "total_kv_transfer_blocks": 105235, "tpot_stats_s": { "count": 4440.0, "mean": 0.005882534704321737, "p50": 0.005807478777200416, "p90": 0.00712956755887717, "p99": 0.008372141476720572 }, "trace_path": "outputs/qwen3-30b-tp1-v3-kvaware/kvcache-centric-kv-aware-worker-admission-20260428T104343Z/sampled-trace.jsonl", "truncated_request_count": 42, "ttft_stats_s": { "count": 4440.0, "mean": 2.2045287611873334, "p50": 0.32809355948120356, "p90": 6.947275545448065, "p99": 16.705802395939827 } } [2026-04-28 19:30:38] Saved to outputs/qwen3-30b-tp1-v3-kvaware/exp2_2p6d_kvc_kvaware_summary.json + exp2_2p6d_kvc_kvaware_metrics.jsonl [2026-04-28 19:30:38] [2026-04-28 19:30:38] === ALL TP1 V3 SWEEP EXPERIMENTS DONE ===