[2026-04-28 20:50:21] Starting TP1 v4 sweep (KVC kv-aware, session soft_cap raised 4->16) [2026-04-28 20:50:21] Model: /mnt/kzlin/workflow/pd-hybrid/simm-swe-bench/models/Qwen3-30B-A3B-Instruct-2507 [2026-04-28 20:50:21] Trace: outputs/qwen35-swebench-50sess.jsonl (4449 requests, 52 sessions) [2026-04-28 20:50:21] Key change: _decode_session_soft_cap now min(16, ...) instead of min(4, ...) [2026-04-28 20:50:21] [2026-04-28 20:50:21] === [EXP1] 1P7D KVC kv-aware cap=16 === [2026-04-28 21:40:57] === exp1_1p7d_kvc_cap16 COMPLETED === [2026-04-28 21:40:57] Summary: { "actual_output_tokens_stats": { "count": 4014.0, "mean": 215.048081714001, "p50": 83.0, "p90": 570.0, "p99": 1343.0 }, "cache_hit_request_count": 3865, "cached_tokens_stats": { "count": 4449.0, "mean": 21373.60867610699, "p50": 18429.0, "p90": 45643.0, "p99": 65088.0 }, "decode_request_priorities": {}, "error_count": 435, "execution_modes": { "kvcache-centric": 435, "kvcache-direct-to-d-session": 2180, "pd-router-d-session-reseed": 44, "pd-router-d-session-reseed-after-eviction": 1, "pd-router-fallback-d-backpressure": 36, "pd-router-fallback-large-append": 35, "pd-router-fallback-large-append-seed-filter-early-turn": 52, "pd-router-fallback-large-append-session-cap": 1500, "pd-router-fallback-no-d-capacity": 13, "pd-router-fallback-session-cap": 43, "pd-router-large-append-reseed": 55, "pd-router-large-append-reseed-after-eviction": 3, "pd-router-turn1-d-backpressure": 1, "pd-router-turn1-no-d-capacity": 5, "pd-router-turn1-seed": 46 }, "latency_stats_s": { "count": 4014.0, "mean": 4.214657033050009, "p50": 1.0827504023909569, "p90": 13.380241627804935, "p99": 24.453291333280504 }, "mechanisms": { "kvcache-centric": 4449 }, "per_decode_load": { "decode-0": 690, "decode-1": 599, "decode-2": 660, "decode-3": 584, "decode-4": 606, "decode-5": 646, "decode-6": 664 }, "per_prefill_load": { "prefill-0": 4449 }, "prefill_request_priorities": { "-100": 149, "100": 1685 }, "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": 2180, "total_actual_kv_transfer_blocks": 52857, "total_cached_tokens": 95091185, "total_kv_transfer_blocks": 105235, "tpot_stats_s": { "count": 4014.0, "mean": 0.005804301410418847, "p50": 0.005607025208882987, "p90": 0.007293824862528552, "p99": 0.008864479259402893 }, "trace_path": "outputs/qwen3-30b-tp1-v4-cap16/kvcache-centric-kv-aware-worker-admission-20260428T125022Z/sampled-trace.jsonl", "truncated_request_count": 43, "ttft_stats_s": { "count": 4014.0, "mean": 2.915135478307124, "p50": 0.05643345229327679, "p90": 11.900803190656006, "p99": 22.758968392387033 } } [2026-04-28 21:40:57] Saved to outputs/qwen3-30b-tp1-v4-cap16/exp1_1p7d_kvc_cap16_summary.json + exp1_1p7d_kvc_cap16_metrics.jsonl [2026-04-28 21:40:57] [2026-04-28 21:40:57] === [EXP2] 2P6D KVC kv-aware cap=16 === [2026-04-28 22:27:53] === exp2_2p6d_kvc_cap16 COMPLETED === [2026-04-28 22:27:53] Summary: { "actual_output_tokens_stats": { "count": 4046.0, "mean": 224.65002471576867, "p50": 84.0, "p90": 576.0, "p99": 1349.0 }, "cache_hit_request_count": 3925, "cached_tokens_stats": { "count": 4449.0, "mean": 22852.7439874129, "p50": 19584.0, "p90": 49009.0, "p99": 67320.0 }, "decode_request_priorities": {}, "error_count": 403, "execution_modes": { "kvcache-centric": 403, "kvcache-direct-to-d-session": 2348, "pd-router-d-session-reseed": 28, "pd-router-fallback-d-backpressure": 7, "pd-router-fallback-large-append": 68, "pd-router-fallback-large-append-seed-filter-early-turn": 45, "pd-router-fallback-large-append-session-cap": 1403, "pd-router-fallback-no-d-capacity": 9, "pd-router-fallback-session-cap": 25, "pd-router-large-append-reseed": 57, "pd-router-large-append-reseed-after-eviction": 6, "pd-router-turn1-no-d-capacity": 1, "pd-router-turn1-seed": 49 }, "latency_stats_s": { "count": 4046.0, "mean": 2.505981629502371, "p50": 0.8372491216287017, "p90": 6.5139341270551085, "p99": 18.335972285829484 }, "mechanisms": { "kvcache-centric": 4449 }, "per_decode_load": { "decode-0": 767, "decode-1": 680, "decode-2": 906, "decode-3": 818, "decode-4": 800, "decode-5": 478 }, "per_prefill_load": { "prefill-0": 2225, "prefill-1": 2224 }, "prefill_request_priorities": { "-100": 140, "100": 1558 }, "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": 2348, "total_actual_kv_transfer_blocks": 50727, "total_cached_tokens": 101671858, "total_kv_transfer_blocks": 105235, "tpot_stats_s": { "count": 4046.0, "mean": 0.005708743129332261, "p50": 0.005565466725497757, "p90": 0.006912594398356141, "p99": 0.008102089307750717 }, "trace_path": "outputs/qwen3-30b-tp1-v4-cap16/kvcache-centric-kv-aware-worker-admission-20260428T134057Z/sampled-trace.jsonl", "truncated_request_count": 36, "ttft_stats_s": { "count": 4046.0, "mean": 1.1653790952959129, "p50": 0.05140436999499798, "p90": 2.6447059931233525, "p99": 15.121314341202378 } } [2026-04-28 22:27:53] Saved to outputs/qwen3-30b-tp1-v4-cap16/exp2_2p6d_kvc_cap16_summary.json + exp2_2p6d_kvc_cap16_metrics.jsonl [2026-04-28 22:27:53] [2026-04-28 22:27:53] === ALL TP1 V4 SWEEP EXPERIMENTS DONE ===