gahow/agentic-kvc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
dc8e6dd5a87869be4fe47a281023ecf9900f2578
agentic-kvc/v2/exp_a_tier_latency/results/rdma.json
Gahow Wang dc8e6dd5a8 v2 exp(a): add remote KV-store (RDMA) tier 
Extends the hit-latency microbench to a 4th tier: a remote global-KV-store
hit over RDMA, the Mooncake-Store mechanism. Two kv_both MooncakeConnector
instances (run_rdma.sh); for each prefix length, instance B serves the
request by pulling instance A's cached prefix over RDMA (do_remote_prefill,
via microbench/fresh_setup/mb2_kv_transfer.py) instead of recomputing -- the
timed pull is the remote-hit latency.

Result (TTFT p50, 11 reps): strict tier ordering
GPU(HBM) < CPU(local DRAM) < remote-RDMA-store << miss, gaps growing with
context. At 64k: GPU 0.11s, CPU 0.27s, RDMA 0.97s, miss 15.2s -> miss/RDMA
15.8x, RDMA/CPU 3.6x, CPU/GPU 2.4x. So a global RDMA store is a real win
over recompute (the blog's 46x) but pays the NIC tax (~5-7 GB/s effective)
and sits a tier below local CPU and two below GPU -- reinforcing
GPU-hit-first. README + figure updated to four tiers.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-30 12:48:37 +08:00

1013 lines
34 KiB
JSON
Raw Blame History

{
"model": "/home/admin/cpfs/wjh/models/Qwen/Qwen3-Coder-30B-A3B-Instruct",
"kv_bytes_per_token": 98304,
"src_host": "127.0.0.1",
"src_port": 8000,
"dst_host": "127.0.0.1",
"dst_port": 8001,
"config_label": "rdma-intra-node",
"raw": [
{
"input_tokens": 1024,
"session": "42945df8aa2947dea7856aec043953c4",
"t_step1_client_unix": 1780113654.6796737,
"t_step2_client_unix": 1780113655.3103006,
"t_step2_end_unix": 1780113655.7742817,
"t_prefill_s": 0.630586825980572,
"t_transfer_s": 0.46393222000915557,
"t_followup_s": 0.09882230299990624,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 1024,
"session": "574133556117480ea4433033ee16ef7d",
"t_step1_client_unix": 1780113655.8735948,
"t_step2_client_unix": 1780113655.9512424,
"t_step2_end_unix": 1780113656.0120106,
"t_prefill_s": 0.07761351700173691,
"t_transfer_s": 0.06073612501495518,
"t_followup_s": 0.047241352003766224,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 1024,
"session": "74de5f623dda4e3ab9bef978237c058a",
"t_step1_client_unix": 1780113656.0597408,
"t_step2_client_unix": 1780113656.136515,
"t_step2_end_unix": 1780113656.1980197,
"t_prefill_s": 0.07674612698610872,
"t_transfer_s": 0.06146429298678413,
"t_followup_s": 0.04567234200658277,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 1024,
"session": "ae5339f421184215a06ee0406d70c6db",
"t_step1_client_unix": 1780113656.2442205,
"t_step2_client_unix": 1780113656.3202548,
"t_step2_end_unix": 1780113656.3829181,
"t_prefill_s": 0.07600510100019164,
"t_transfer_s": 0.06263405701611191,
"t_followup_s": 0.045199740008683875,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 1024,
"session": "108018399ef64e66a9780f032bd5f1d2",
"t_step1_client_unix": 1780113656.4285796,
"t_step2_client_unix": 1780113656.5039103,
"t_step2_end_unix": 1780113656.5650918,
"t_prefill_s": 0.07530323401442729,
"t_transfer_s": 0.06115360799594782,
"t_followup_s": 0.047417668014531955,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 1024,
"session": "4f147b3685f348599ee6d31f592d3d68",
"t_step1_client_unix": 1780113656.613002,
"t_step2_client_unix": 1780113656.688678,
"t_step2_end_unix": 1780113656.7499766,
"t_prefill_s": 0.07563983497675508,
"t_transfer_s": 0.061254432977875695,
"t_followup_s": 0.05035233299713582,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 1024,
"session": "7185314a355d4fb1a7be63667bb5d532",
"t_step1_client_unix": 1780113656.8008058,
"t_step2_client_unix": 1780113656.876437,
"t_step2_end_unix": 1780113656.9365327,
"t_prefill_s": 0.0756044389854651,
"t_transfer_s": 0.0600691509898752,
"t_followup_s": 0.04694663899135776,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 1024,
"session": "a75befce806b49ca8b4bc839d398a836",
"t_step1_client_unix": 1780113656.9840212,
"t_step2_client_unix": 1780113657.0596485,
"t_step2_end_unix": 1780113657.121014,
"t_prefill_s": 0.07559421702171676,
"t_transfer_s": 0.061336473998380825,
"t_followup_s": 0.04504776999237947,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 1024,
"session": "5eed050534974087b585636f8626d36b",
"t_step1_client_unix": 1780113657.1665282,
"t_step2_client_unix": 1780113657.2422314,
"t_step2_end_unix": 1780113657.3042758,
"t_prefill_s": 0.07567335499334149,
"t_transfer_s": 0.062015656993025914,
"t_followup_s": 0.044170998997287825,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 1024,
"session": "38ad990f52254bf39487a0ba49780d8b",
"t_step1_client_unix": 1780113657.3489134,
"t_step2_client_unix": 1780113657.425841,
"t_step2_end_unix": 1780113657.485667,
"t_prefill_s": 0.07690018997527659,
"t_transfer_s": 0.05979751900304109,
"t_followup_s": 0.047392740001669154,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 1024,
"session": "d01e4123b1b54d5e8578ec06bcb198f0",
"t_step1_client_unix": 1780113657.533507,
"t_step2_client_unix": 1780113657.6109633,
"t_step2_end_unix": 1780113657.673547,
"t_prefill_s": 0.07741417599027045,
"t_transfer_s": 0.0625474060070701,
"t_followup_s": 0.04817350400844589,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 2048,
"session": "62ff1956604d459e84052715e7ed8ba7",
"t_step1_client_unix": 1780113657.7226295,
"t_step2_client_unix": 1780113657.9077578,
"t_step2_end_unix": 1780113657.985153,
"t_prefill_s": 0.18509869498666376,
"t_transfer_s": 0.07735455100191757,
"t_followup_s": 0.046408719004830346,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 2048,
"session": "ec7b97db9dae4bc888c91b65c5efabba",
"t_step1_client_unix": 1780113658.0324116,
"t_step2_client_unix": 1780113658.1642551,
"t_step2_end_unix": 1780113658.2397475,
"t_prefill_s": 0.1318151500017848,
"t_transfer_s": 0.07546432898379862,
"t_followup_s": 0.04965048600570299,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 2048,
"session": "082ed4f2baec4107acf0dbebabbcf32f",
"t_step1_client_unix": 1780113658.2902431,
"t_step2_client_unix": 1780113658.4218829,
"t_step2_end_unix": 1780113658.494315,
"t_prefill_s": 0.1316128930193372,
"t_transfer_s": 0.07240396799170412,
"t_followup_s": 0.04556456100544892,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 2048,
"session": "890e243bc7f742c19a899cd19160e6ce",
"t_step1_client_unix": 1780113658.540683,
"t_step2_client_unix": 1780113658.6717823,
"t_step2_end_unix": 1780113658.7469842,
"t_prefill_s": 0.13105839598574676,
"t_transfer_s": 0.07517452799947932,
"t_followup_s": 0.04641962700407021,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 2048,
"session": "e4ca5aef90be4b45bc2222ad3c637581",
"t_step1_client_unix": 1780113658.7943006,
"t_step2_client_unix": 1780113658.9255776,
"t_step2_end_unix": 1780113659.0016084,
"t_prefill_s": 0.13125143098295666,
"t_transfer_s": 0.07600446898140945,
"t_followup_s": 0.04827121601556428,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 2048,
"session": "64e21909088043e98e7532361d747128",
"t_step1_client_unix": 1780113659.0507092,
"t_step2_client_unix": 1780113659.1820831,
"t_step2_end_unix": 1780113659.2554085,
"t_prefill_s": 0.13133879398810677,
"t_transfer_s": 0.07329847698565573,
"t_followup_s": 0.050039641006151214,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 2048,
"session": "8d3cb21a4f1a4daa94d31a48d969188a",
"t_step1_client_unix": 1780113659.3063629,
"t_step2_client_unix": 1780113659.437705,
"t_step2_end_unix": 1780113659.5105412,
"t_prefill_s": 0.13131436699768528,
"t_transfer_s": 0.07280980699579231,
"t_followup_s": 0.045990444981725886,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 2048,
"session": "a949f45bf00e4b6f9e282a48d2f54ae9",
"t_step1_client_unix": 1780113659.5574262,
"t_step2_client_unix": 1780113659.6894715,
"t_step2_end_unix": 1780113659.763246,
"t_prefill_s": 0.13201635199948214,
"t_transfer_s": 0.07374655400053598,
"t_followup_s": 0.04740602700621821,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 2048,
"session": "a1350bc4af1d4a95a8d7870aac6c30d4",
"t_step1_client_unix": 1780113659.8115327,
"t_step2_client_unix": 1780113659.94307,
"t_step2_end_unix": 1780113660.0165753,
"t_prefill_s": 0.13151001499500126,
"t_transfer_s": 0.07347742197453044,
"t_followup_s": 0.054559190990403295,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 2048,
"session": "0cbada3f1cf34ad98150c7cd05df9e81",
"t_step1_client_unix": 1780113660.0719872,
"t_step2_client_unix": 1780113660.2065787,
"t_step2_end_unix": 1780113660.2800386,
"t_prefill_s": 0.13456111898995005,
"t_transfer_s": 0.07343242000206374,
"t_followup_s": 0.04842582900892012,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 2048,
"session": "086166dcac9f4cf587152003a665dd6d",
"t_step1_client_unix": 1780113660.3293216,
"t_step2_client_unix": 1780113660.4612148,
"t_step2_end_unix": 1780113660.5348513,
"t_prefill_s": 0.13186514400877059,
"t_transfer_s": 0.07360914399032481,
"t_followup_s": 0.04667951900046319,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 4096,
"session": "e16840958b4e42378aa2f474224f7c47",
"t_step1_client_unix": 1780113660.5832062,
"t_step2_client_unix": 1780113660.8487082,
"t_step2_end_unix": 1780113660.9490895,
"t_prefill_s": 0.26547358598327264,
"t_transfer_s": 0.10033372900215909,
"t_followup_s": 0.04891211100039072,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 4096,
"session": "8119bfc1b947496e8434bc2dd780ddf2",
"t_step1_client_unix": 1780113660.9995859,
"t_step2_client_unix": 1780113661.2600472,
"t_step2_end_unix": 1780113661.3582017,
"t_prefill_s": 0.2604305710119661,
"t_transfer_s": 0.09812465400318615,
"t_followup_s": 0.0544344789814204,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 4096,
"session": "cb517bfea1ac46058ffbf918582c74d4",
"t_step1_client_unix": 1780113661.414242,
"t_step2_client_unix": 1780113661.674581,
"t_step2_end_unix": 1780113661.7718108,
"t_prefill_s": 0.2603055170038715,
"t_transfer_s": 0.09719818198936991,
"t_followup_s": 0.0503446809889283,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 4096,
"session": "89eabc4ad0534b4a934b1e852050c6f5",
"t_step1_client_unix": 1780113661.823718,
"t_step2_client_unix": 1780113662.0844855,
"t_step2_end_unix": 1780113662.1830976,
"t_prefill_s": 0.2607354299980216,
"t_transfer_s": 0.09858069600886665,
"t_followup_s": 0.04950785997789353,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 4096,
"session": "b644572bba324d829a249aaeeb22ee54",
"t_step1_client_unix": 1780113662.2342994,
"t_step2_client_unix": 1780113662.4946663,
"t_step2_end_unix": 1780113662.5922973,
"t_prefill_s": 0.26033472700510174,
"t_transfer_s": 0.09760292299324647,
"t_followup_s": 0.05018276898772456,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 4096,
"session": "01faaeab31bd4feb9b27bd03e5ee75b1",
"t_step1_client_unix": 1780113662.6441038,
"t_step2_client_unix": 1780113662.9044588,
"t_step2_end_unix": 1780113663.0019135,
"t_prefill_s": 0.26032789101009257,
"t_transfer_s": 0.09742468598415144,
"t_followup_s": 0.0510591670172289,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 4096,
"session": "87a72e6be33b46c29035ea566f1c79cc",
"t_step1_client_unix": 1780113663.0545735,
"t_step2_client_unix": 1780113663.315426,
"t_step2_end_unix": 1780113663.415479,
"t_prefill_s": 0.2608224749856163,
"t_transfer_s": 0.10002275300212204,
"t_followup_s": 0.05161238700384274,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 4096,
"session": "28b5629f8b04451d9404f5dd15b860a0",
"t_step1_client_unix": 1780113663.4687288,
"t_step2_client_unix": 1780113663.7299144,
"t_step2_end_unix": 1780113663.8311837,
"t_prefill_s": 0.26115050600492395,
"t_transfer_s": 0.10123400299926288,
"t_followup_s": 0.04951982302009128,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 4096,
"session": "ed022f1b155c4fe191032d8c917124c5",
"t_step1_client_unix": 1780113663.882292,
"t_step2_client_unix": 1780113664.1436367,
"t_step2_end_unix": 1780113664.2428293,
"t_prefill_s": 0.2613153549900744,
"t_transfer_s": 0.0991641900036484,
"t_followup_s": 0.05027229798724875,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 4096,
"session": "cb09310c2178452cb2ecda3f4c4f4642",
"t_step1_client_unix": 1780113664.2947013,
"t_step2_client_unix": 1780113664.5561187,
"t_step2_end_unix": 1780113664.6587803,
"t_prefill_s": 0.2613755869970191,
"t_transfer_s": 0.10260535500128753,
"t_followup_s": 0.054842573998030275,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 4096,
"session": "26a14c40b7424663ad5bf012e04b0d48",
"t_step1_client_unix": 1780113664.7152772,
"t_step2_client_unix": 1780113664.9784563,
"t_step2_end_unix": 1780113665.0804708,
"t_prefill_s": 0.2631347790011205,
"t_transfer_s": 0.10197760400478728,
"t_followup_s": 0.05454107699915767,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 8192,
"session": "28aa179a55b04b6e826df76997e49965",
"t_step1_client_unix": 1780113665.1381943,
"t_step2_client_unix": 1780113665.725791,
"t_step2_end_unix": 1780113665.8781552,
"t_prefill_s": 0.587549192016013,
"t_transfer_s": 0.15232679099426605,
"t_followup_s": 0.05964333200245164,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 8192,
"session": "c947ef89013d420faf4784bd0e0d5532",
"t_step1_client_unix": 1780113665.9409757,
"t_step2_client_unix": 1780113666.5288377,
"t_step2_end_unix": 1780113666.677537,
"t_prefill_s": 0.5878257739823312,
"t_transfer_s": 0.14866453199647367,
"t_followup_s": 0.05501791799906641,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 8192,
"session": "c71d8f7e44454f208391211b91409f34",
"t_step1_client_unix": 1780113666.7356484,
"t_step2_client_unix": 1780113667.3223348,
"t_step2_end_unix": 1780113667.475447,
"t_prefill_s": 0.5866534260276239,
"t_transfer_s": 0.15308237000135705,
"t_followup_s": 0.06039133798913099,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 8192,
"session": "d2f1c3b53ea8409ca49d5b6bcc7bea2a",
"t_step1_client_unix": 1780113667.5389588,
"t_step2_client_unix": 1780113668.1259756,
"t_step2_end_unix": 1780113668.2758486,
"t_prefill_s": 0.5869663549819961,
"t_transfer_s": 0.14983698999276385,
"t_followup_s": 0.05716336300247349,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 8192,
"session": "2b5edf5a21cc44f5929a722322d89d52",
"t_step1_client_unix": 1780113668.3363352,
"t_step2_client_unix": 1780113668.9260604,
"t_step2_end_unix": 1780113669.079605,
"t_prefill_s": 0.5896447559935041,
"t_transfer_s": 0.15350710399798118,
"t_followup_s": 0.05581469400203787,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 8192,
"session": "3d29eed43ca644ab998a89ae996521a0",
"t_step1_client_unix": 1780113669.1385791,
"t_step2_client_unix": 1780113669.7260985,
"t_step2_end_unix": 1780113669.8774042,
"t_prefill_s": 0.5874853960121982,
"t_transfer_s": 0.15127158901304938,
"t_followup_s": 0.057220480986870825,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 8192,
"session": "657303232eec4008abdc80cb69e27508",
"t_step1_client_unix": 1780113669.937695,
"t_step2_client_unix": 1780113670.5248249,
"t_step2_end_unix": 1780113670.6737514,
"t_prefill_s": 0.5870937670115381,
"t_transfer_s": 0.14888012100709602,
"t_followup_s": 0.059168930019950494,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 8192,
"session": "3560bebf9f7d4138b33cd30dd16aacfd",
"t_step1_client_unix": 1780113670.7366655,
"t_step2_client_unix": 1780113671.3249788,
"t_step2_end_unix": 1780113671.477699,
"t_prefill_s": 0.5882545940112323,
"t_transfer_s": 0.1526875200215727,
"t_followup_s": 0.06097331500495784,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 8192,
"session": "a8bb4afeb02b4ff99eac92226f0d5f58",
"t_step1_client_unix": 1780113671.5417728,
"t_step2_client_unix": 1780113672.1291869,
"t_step2_end_unix": 1780113672.280071,
"t_prefill_s": 0.5873805590090342,
"t_transfer_s": 0.15085255599115044,
"t_followup_s": 0.057901772001059726,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 8192,
"session": "68c32fca0260409c8a632ff617513587",
"t_step1_client_unix": 1780113672.3411584,
"t_step2_client_unix": 1780113672.9282277,
"t_step2_end_unix": 1780113673.0856972,
"t_prefill_s": 0.5870382410066668,
"t_transfer_s": 0.15743795299204066,
"t_followup_s": 0.05747991299722344,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 8192,
"session": "b95e321ef53e4383b302c2db7ebcca73",
"t_step1_client_unix": 1780113673.1462142,
"t_step2_client_unix": 1780113673.7336242,
"t_step2_end_unix": 1780113673.8830152,
"t_prefill_s": 0.5873774820065591,
"t_transfer_s": 0.149357913993299,
"t_followup_s": 0.05543989400030114,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 16384,
"session": "0979f595e2b44f3285b4242fda1ee3df",
"t_step1_client_unix": 1780113673.9444556,
"t_step2_client_unix": 1780113675.5027504,
"t_step2_end_unix": 1780113675.7646046,
"t_prefill_s": 1.558238979021553,
"t_transfer_s": 0.2618165699823294,
"t_followup_s": 0.07395038701361045,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 16384,
"session": "14c8c786b4a846149945ea141f705863",
"t_step1_client_unix": 1780113675.8444831,
"t_step2_client_unix": 1780113677.3960428,
"t_step2_end_unix": 1780113677.6459343,
"t_prefill_s": 1.5515160829818342,
"t_transfer_s": 0.249856763985008,
"t_followup_s": 0.06939491498633288,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 16384,
"session": "31d3cb21ac8d4ced89ab33ce4fb7589b",
"t_step1_client_unix": 1780113677.721303,
"t_step2_client_unix": 1780113679.2696404,
"t_step2_end_unix": 1780113679.5167441,
"t_prefill_s": 1.548295495013008,
"t_transfer_s": 0.24705595700652339,
"t_followup_s": 0.06773578398860991,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 16384,
"session": "a9d5cbce333f4c21afaa8bdbeab31bf3",
"t_step1_client_unix": 1780113679.5905588,
"t_step2_client_unix": 1780113681.1353347,
"t_step2_end_unix": 1780113681.37527,
"t_prefill_s": 1.5447358399978839,
"t_transfer_s": 0.23989686000277288,
"t_followup_s": 0.06704856699798256,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 16384,
"session": "e58110ad40cc46e0b15b222ebf0cbe86",
"t_step1_client_unix": 1780113681.4499586,
"t_step2_client_unix": 1780113682.9963198,
"t_step2_end_unix": 1780113683.2421525,
"t_prefill_s": 1.5463133199955337,
"t_transfer_s": 0.2457908419892192,
"t_followup_s": 0.06450486500398256,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 16384,
"session": "fbec8cdaac0c4ef8a028c68e49311b9a",
"t_step1_client_unix": 1780113683.3127434,
"t_step2_client_unix": 1780113684.8600428,
"t_step2_end_unix": 1780113685.106106,
"t_prefill_s": 1.5472517309826799,
"t_transfer_s": 0.2460192689904943,
"t_followup_s": 0.06439224901259877,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 16384,
"session": "7598055ceec1423d9b1d88c6200a1c21",
"t_step1_client_unix": 1780113685.1769145,
"t_step2_client_unix": 1780113686.732929,
"t_step2_end_unix": 1780113687.0007024,
"t_prefill_s": 1.5559708710061386,
"t_transfer_s": 0.2677336060150992,
"t_followup_s": 0.06560050300322473,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 16384,
"session": "f0512699fd10499ebb2421087d5138cc",
"t_step1_client_unix": 1780113687.0725183,
"t_step2_client_unix": 1780113688.6251225,
"t_step2_end_unix": 1780113688.9931352,
"t_prefill_s": 1.5525663039879873,
"t_transfer_s": 0.3679773240000941,
"t_followup_s": 0.07065863799653016,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 16384,
"session": "818876ee380f4a8f9258ddff7554e718",
"t_step1_client_unix": 1780113689.0700693,
"t_step2_client_unix": 1780113690.6202304,
"t_step2_end_unix": 1780113690.976204,
"t_prefill_s": 1.5501246719795745,
"t_transfer_s": 0.3559349720017053,
"t_followup_s": 0.06182111200178042,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 16384,
"session": "440b924a8dc44a57a60a8d8790b83425",
"t_step1_client_unix": 1780113691.0440626,
"t_step2_client_unix": 1780113692.600122,
"t_step2_end_unix": 1780113692.9298801,
"t_prefill_s": 1.5560206689988263,
"t_transfer_s": 0.3297227440052666,
"t_followup_s": 0.06168726898613386,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 16384,
"session": "bf7c1545c5a048b497c4934e849d9b77",
"t_step1_client_unix": 1780113692.9983332,
"t_step2_client_unix": 1780113694.549985,
"t_step2_end_unix": 1780113694.902612,
"t_prefill_s": 1.5515996039903257,
"t_transfer_s": 0.3525931639887858,
"t_followup_s": 0.06388000200968236,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 32768,
"session": "3ea99ff99c034fadaae11e0a18cbcd12",
"t_step1_client_unix": 1780113694.978447,
"t_step2_client_unix": 1780113699.5872533,
"t_step2_end_unix": 1780113700.3202353,
"t_prefill_s": 4.608766862016637,
"t_transfer_s": 0.7329461979970802,
"t_followup_s": 0.08203631298965774,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 32768,
"session": "160f663843cc4da4a4c1968620e74bbe",
"t_step1_client_unix": 1780113700.4144092,
"t_step2_client_unix": 1780113705.0188375,
"t_step2_end_unix": 1780113705.7512634,
"t_prefill_s": 4.604390962980688,
"t_transfer_s": 0.7323910310224164,
"t_followup_s": 0.08162634400650859,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 32768,
"session": "44be5da3d4d9421ea682b02af879f038",
"t_step1_client_unix": 1780113705.8446133,
"t_step2_client_unix": 1780113710.446565,
"t_step2_end_unix": 1780113711.1756835,
"t_prefill_s": 4.60191403501085,
"t_transfer_s": 0.7290820410125889,
"t_followup_s": 0.08314321600482799,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 32768,
"session": "76fb5e99bda74949ab48c2a806796e20",
"t_step1_client_unix": 1780113711.2712142,
"t_step2_client_unix": 1780113715.8831358,
"t_step2_end_unix": 1780113716.605932,
"t_prefill_s": 4.611884240992367,
"t_transfer_s": 0.7227587410015985,
"t_followup_s": 0.08411424100631848,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 32768,
"session": "2698392640df43d98c5b88ec14603ab4",
"t_step1_client_unix": 1780113716.7025611,
"t_step2_client_unix": 1780113721.3066654,
"t_step2_end_unix": 1780113721.9864836,
"t_prefill_s": 4.60406794998562,
"t_transfer_s": 0.6797809940180741,
"t_followup_s": 0.0797950770065654,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 32768,
"session": "3a317d68c23d48a6b464cbb7471f1b15",
"t_step1_client_unix": 1780113722.078643,
"t_step2_client_unix": 1780113726.683183,
"t_step2_end_unix": 1780113727.3790748,
"t_prefill_s": 4.604500039014965,
"t_transfer_s": 0.6958539690240286,
"t_followup_s": 0.0791638570080977,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 32768,
"session": "ef55cea31d1d4c9faa3095c6572b3158",
"t_step1_client_unix": 1780113727.4699852,
"t_step2_client_unix": 1780113732.0734339,
"t_step2_end_unix": 1780113732.6349242,
"t_prefill_s": 4.603411051008152,
"t_transfer_s": 0.5614562759874389,
"t_followup_s": 0.07942970001022331,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 32768,
"session": "51111cf4420040aabc709ec95b69299c",
"t_step1_client_unix": 1780113732.726002,
"t_step2_client_unix": 1780113737.3279588,
"t_step2_end_unix": 1780113737.768525,
"t_prefill_s": 4.6019097800017335,
"t_transfer_s": 0.4405296350014396,
"t_followup_s": 0.07934816100168973,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 32768,
"session": "a4218f26139940b7a63c574c58c0cc78",
"t_step1_client_unix": 1780113737.8595614,
"t_step2_client_unix": 1780113742.4654746,
"t_step2_end_unix": 1780113742.9027445,
"t_prefill_s": 4.605869954015361,
"t_transfer_s": 0.43722251401050016,
"t_followup_s": 0.08265988298808224,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 32768,
"session": "ef166eea7c0241a0b6683c9b9be98e26",
"t_step1_client_unix": 1780113742.9973059,
"t_step2_client_unix": 1780113747.60252,
"t_step2_end_unix": 1780113748.0344896,
"t_prefill_s": 4.605175297008827,
"t_transfer_s": 0.43193520401837304,
"t_followup_s": 0.08029142298619263,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 32768,
"session": "510b2beab0934d4191ce4c4b4fb8bb20",
"t_step1_client_unix": 1780113748.1287684,
"t_step2_client_unix": 1780113752.728051,
"t_step2_end_unix": 1780113753.1700265,
"t_prefill_s": 4.599246629979461,
"t_transfer_s": 0.4419387440138962,
"t_followup_s": 0.08067455000127666,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 65536,
"session": "d51ed2927db344808d34fac0c09d5d29",
"t_step1_client_unix": 1780113753.274224,
"t_step2_client_unix": 1780113768.560607,
"t_step2_end_unix": 1780113769.367652,
"t_prefill_s": 15.286344999010907,
"t_transfer_s": 0.8070085129875224,
"t_followup_s": 0.11767313402378932,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 65536,
"session": "a7af94a6de9547b4b943c986b7e6f001",
"t_step1_client_unix": 1780113769.5093763,
"t_step2_client_unix": 1780113784.8304524,
"t_step2_end_unix": 1780113785.7471335,
"t_prefill_s": 15.31890859498526,
"t_transfer_s": 0.9138955899979919,
"t_followup_s": 0.1327741070126649,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 65536,
"session": "48300f75fbb347e6859a6a0585dcc04e",
"t_step1_client_unix": 1780113785.9058163,
"t_step2_client_unix": 1780113801.193769,
"t_step2_end_unix": 1780113802.842876,
"t_prefill_s": 15.287883285986027,
"t_transfer_s": 1.6490699610149022,
"t_followup_s": 0.10919595797895454,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 65536,
"session": "c61d6f9f29024284b284f54d907d5fc9",
"t_step1_client_unix": 1780113802.975333,
"t_step2_client_unix": 1780113818.271725,
"t_step2_end_unix": 1780113820.8995724,
"t_prefill_s": 15.296337511012098,
"t_transfer_s": 2.6278096020105295,
"t_followup_s": 0.12072346499189734,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 65536,
"session": "52ef9ee529ef44d7b6140535833c05a3",
"t_step1_client_unix": 1780113821.0437183,
"t_step2_client_unix": 1780113836.3338494,
"t_step2_end_unix": 1780113838.7353442,
"t_prefill_s": 15.290092708019074,
"t_transfer_s": 2.4014571599836927,
"t_followup_s": 0.11354603400104679,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 65536,
"session": "99730c3c4684499286c1831c027e3b39",
"t_step1_client_unix": 1780113838.8726406,
"t_step2_client_unix": 1780113854.1566162,
"t_step2_end_unix": 1780113855.7166855,
"t_prefill_s": 15.283936669002287,
"t_transfer_s": 1.560034744994482,
"t_followup_s": 0.11488680701586418,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 65536,
"session": "6f072e8c09734c2cb3ff771c538b80c5",
"t_step1_client_unix": 1780113855.8550732,
"t_step2_client_unix": 1780113871.1431854,
"t_step2_end_unix": 1780113872.1094413,
"t_prefill_s": 15.288075597025454,
"t_transfer_s": 0.9662203160114586,
"t_followup_s": 0.11588297100388445,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 65536,
"session": "6bd7c6a2a8614f0a8ab32ad7b6fdc6da",
"t_step1_client_unix": 1780113872.2491899,
"t_step2_client_unix": 1780113887.532155,
"t_step2_end_unix": 1780113888.451564,
"t_prefill_s": 15.282926287996816,
"t_transfer_s": 0.9193728909885976,
"t_followup_s": 0.11174739900161512,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 65536,
"session": "03936c26f94947539251b7a8fe429eb5",
"t_step1_client_unix": 1780113888.5874689,
"t_step2_client_unix": 1780113903.8650937,
"t_step2_end_unix": 1780113904.6822457,
"t_prefill_s": 15.277585066010943,
"t_transfer_s": 0.8171155720192473,
"t_followup_s": 0.11233539402019233,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 65536,
"session": "fbef8e1b6fd94f28b8e0edbc86135cf5",
"t_step1_client_unix": 1780113904.8176143,
"t_step2_client_unix": 1780113920.1035478,
"t_step2_end_unix": 1780113921.0166585,
"t_prefill_s": 15.285897619993193,
"t_transfer_s": 0.9130747889867052,
"t_followup_s": 0.13272951598628424,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
},
{
"input_tokens": 65536,
"session": "526e3b3a3df64dea9e513e7bb9c3da53",
"t_step1_client_unix": 1780113921.172305,
"t_step2_client_unix": 1780113936.4544415,
"t_step2_end_unix": 1780113937.868287,
"t_prefill_s": 15.282098516006954,
"t_transfer_s": 1.4137536820198875,
"t_followup_s": 0.11649087502155453,
"cached_followup": 0,
"pull_completion_tokens": 1,
"ok": false
}
],
"summary": []
}
Reference in New Issue View Git Blame Copy Permalink