docs: v4 final results, error analysis, and updated journey

Add v4 sweep results and post-mortem analysis showing:

- direct-to-D path: 54.3% (1P7D) / 58.0% (2P6D) of requests now use
  KVC cleanly. P50=0.5s and TTFT P50=0.043s; this path beats baseline
  8DP across the board (P50 -24%, TTFT P50 -54%, TTFT P90 -79%).

- Overall vs baseline (errors+truncated excluded):
  v4 2P6D P50=0.85s vs baseline 0.66s (28% slower).
  Reason is not errors -- 35% of requests still hit
  fallback-large-append-session-cap, where capacity-based
  cap = usable_tokens / target_tokens evaluates to 1-2 (not 16)
  for large agentic inputs.

- 9-10% errors on KVC variants are mooncake TCP transfer timeouts,
  not SGLang logic bugs. Prefill log shows
  "Failed to send kv chunk ... 32s timeout ... session not alive".
  Errors concentrate in turn>=31 (large inputs) after run >44.8%.

Track:
- docs/KVC_DEBUG_JOURNEY_V1_TO_V4.md: append v4 results table,
  per-mode breakdown, and error root cause.
- scripts/analysis/{analyze_v3,analyze_v4,analyze_errors,compare_no_error}.py
- outputs/qwen3-30b-tp1-v{3,4}*/exp*_summary.json (force-added,
  small JSON; metrics.jsonl excluded due to size).
- outputs/qwen3-30b-tp1-v{3,4}*/sweep_results.txt

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
kzlin
2026-04-28 23:34:01 +08:00
parent c9d350b372
commit 74194e660a
11 changed files with 1162 additions and 3 deletions

View File

@@ -0,0 +1,88 @@
{
"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
}
}

View File

@@ -0,0 +1,85 @@
{
"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
}
}

View File

@@ -0,0 +1,189 @@
[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 ===

View File

@@ -0,0 +1,88 @@
{
"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
}
}

View File

@@ -0,0 +1,86 @@
{
"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
}
}

View File

@@ -0,0 +1,190 @@
[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 ===