diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 95e5e9ae0..db350d47f 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -3042,7 +3042,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-09-23T01:33:15.985873+00:00", + "generatedAt": "2026-09-23T01:38:35.453695+00:00", "summary": { "activeBlockCount": 153, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 71c9437ff..c3718b747 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -3,77 +3,77 @@ "communityError": null, "communitySample": {}, "communityUpdatedAt": "2026-09-23T01:29:32.152287+00:00", - "frameworkAttemptedAt": "2026-09-22T22:43:53.208472+00:00", + "frameworkAttemptedAt": "2026-09-23T01:39:44.904617+00:00", "frameworkError": null, "frameworkStats": { "text-generation": { "Ascend_910-b4": { "llamacpp": { "framework": "llamacpp", - "modelCount": 33510, + "modelCount": 33522, "officialConfigError": null, "officialConfigValid": true, - "successCount": 14962, - "successRate": 0.4464935840047747, - "wilsonLowerBound": 0.441177247640571 + "successCount": 14972, + "successRate": 0.44663206252610227, + "wilsonLowerBound": 0.4413165014100769 }, "vllm": { "framework": "vllm", - "modelCount": 37866, + "modelCount": 37885, "officialConfigError": null, "officialConfigValid": true, - "successCount": 10726, - "successRate": 0.2832620292610785, - "wilsonLowerBound": 0.27874576151122477 + "successCount": 10729, + "successRate": 0.28319915533852447, + "wilsonLowerBound": 0.27868432555059713 }, "vllm_tokenizer_patch": { "framework": "vllm_tokenizer_patch", - "modelCount": 9599, + "modelCount": 9619, "officialConfigError": null, "officialConfigValid": true, - "successCount": 4040, - "successRate": 0.4208771747056985, - "wilsonLowerBound": 0.4110341836432966 + "successCount": 4050, + "successRate": 0.42104168832518973, + "wilsonLowerBound": 0.4112083068888436 } }, "Biren_166m": { "vllm": { "framework": "vllm", - "modelCount": 64086, + "modelCount": 64092, "officialConfigError": null, "officialConfigValid": true, "successCount": 12089, - "successRate": 0.18863714383796773, - "wilsonLowerBound": 0.1856268657071267 + "successRate": 0.18861948449104413, + "wilsonLowerBound": 0.18560945625417716 }, "vllm_fix_tokenizer": { "framework": "vllm_fix_tokenizer", - "modelCount": 19605, + "modelCount": 19683, "officialConfigError": null, "officialConfigValid": true, - "successCount": 3959, - "successRate": 0.20193828105075237, - "wilsonLowerBound": 0.19637738902452356 + "successCount": 3976, + "successRate": 0.20200172737895647, + "wilsonLowerBound": 0.1964510780026152 }, "vllm_tokenizer_patch": { "framework": "vllm_tokenizer_patch", - "modelCount": 6341, + "modelCount": 6356, "officialConfigError": null, "officialConfigValid": true, "successCount": 65, - "successRate": 0.010250749093202964, - "wilsonLowerBound": 0.008051117613069435 + "successRate": 0.010226557583385778, + "wilsonLowerBound": 0.008032098669339785 } }, "Cambricon_mlu-370-x4": { "vllm": { "framework": "vllm", - "modelCount": 26221, + "modelCount": 26223, "officialConfigError": null, "officialConfigValid": true, - "successCount": 3232, - "successRate": 0.12325998245680943, - "wilsonLowerBound": 0.11933604232380676 + "successCount": 3233, + "successRate": 0.12328871601266064, + "wilsonLowerBound": 0.11936452080982458 }, "vllm-customized": { "framework": "vllm-customized", @@ -86,23 +86,23 @@ }, "vllm-mlu": { "framework": "vllm-mlu", - "modelCount": 11804, + "modelCount": 11824, "officialConfigError": null, "officialConfigValid": true, - "successCount": 4932, - "successRate": 0.41782446628261605, - "wilsonLowerBound": 0.40895516245122215 + "successCount": 4939, + "successRate": 0.41770974289580515, + "wilsonLowerBound": 0.40884830026001817 } }, "Cambricon_mlu-370-x8": { "vllm": { "framework": "vllm", - "modelCount": 24297, + "modelCount": 24305, "officialConfigError": null, "officialConfigValid": true, "successCount": 3789, - "successRate": 0.15594517841708852, - "wilsonLowerBound": 0.15143764916662947 + "successRate": 0.1558938490022629, + "wilsonLowerBound": 0.15138767266168512 }, "vllm-customized": { "framework": "vllm-customized", @@ -115,88 +115,88 @@ }, "vllm-mlu": { "framework": "vllm-mlu", - "modelCount": 44455, + "modelCount": 44514, "officialConfigError": null, "officialConfigValid": true, - "successCount": 11092, - "successRate": 0.24951074119896524, - "wilsonLowerBound": 0.2455098475218893 + "successCount": 11103, + "successRate": 0.2494271465157029, + "wilsonLowerBound": 0.24542934745078349 } }, "Iluvatar_bi-100": { "transformers": { "framework": "transformers", - "modelCount": 23392, + "modelCount": 23396, "officialConfigError": null, "officialConfigValid": true, "successCount": 3077, - "successRate": 0.13154069767441862, - "wilsonLowerBound": 0.1272697426969564 + "successRate": 0.1315182082407249, + "wilsonLowerBound": 0.12724793098498738 }, "vllm": { "framework": "vllm", - "modelCount": 86712, + "modelCount": 86713, "officialConfigError": null, "officialConfigValid": true, "successCount": 9764, - "successRate": 0.11260263861979887, - "wilsonLowerBound": 0.11051575754028639 + "successRate": 0.11260134005281791, + "wilsonLowerBound": 0.11051448155701736 }, "vllm-patch-tokenizer": { "framework": "vllm-patch-tokenizer", - "modelCount": 41154, + "modelCount": 41166, "officialConfigError": null, "officialConfigValid": true, "successCount": 5061, - "successRate": 0.12297711036594255, - "wilsonLowerBound": 0.11983927163966648 + "successRate": 0.12294126220667541, + "wilsonLowerBound": 0.11980427661360105 }, "vllm_fix_tokenizer": { "framework": "vllm_fix_tokenizer", - "modelCount": 33808, + "modelCount": 33890, "officialConfigError": null, "officialConfigValid": true, "successCount": 3446, - "successRate": 0.10192853762423094, - "wilsonLowerBound": 0.09874848320075474 + "successRate": 0.10168191206845677, + "wilsonLowerBound": 0.09850913754310354 } }, "Iluvatar_bi-150": { "llamacpp": { "framework": "llamacpp", - "modelCount": 89050, + "modelCount": 89059, "officialConfigError": null, "officialConfigValid": true, - "successCount": 21291, - "successRate": 0.23909039865244244, - "wilsonLowerBound": 0.23630021684187955 + "successCount": 21299, + "successRate": 0.23915606508045228, + "wilsonLowerBound": 0.23636575709937582 }, "transformers": { "framework": "transformers", - "modelCount": 5274, + "modelCount": 5275, "officialConfigError": null, "officialConfigValid": true, "successCount": 572, - "successRate": 0.10845657944634055, - "wilsonLowerBound": 0.10034740757776903 + "successRate": 0.10843601895734598, + "wilsonLowerBound": 0.10032830162541802 }, "vllm": { "framework": "vllm", - "modelCount": 112671, + "modelCount": 112673, "officialConfigError": null, "officialConfigValid": true, "successCount": 16519, - "successRate": 0.146612704245103, - "wilsonLowerBound": 0.144559330485228 + "successRate": 0.1466101017990113, + "wilsonLowerBound": 0.1445567614259641 }, "vllm_0_17_0_corex_4_4_0": { "framework": "vllm_0_17_0_corex_4_4_0", - "modelCount": 18292, + "modelCount": 18308, "officialConfigError": null, "officialConfigValid": true, "successCount": 3553, - "successRate": 0.19423791821561337, - "wilsonLowerBound": 0.18856917768660844 + "successRate": 0.19406816692156434, + "wilsonLowerBound": 0.18840381195247902 }, "vllm_fix_tokenizer": { "framework": "vllm_fix_tokenizer", @@ -229,81 +229,81 @@ }, "vllm": { "framework": "vllm", - "modelCount": 31594, + "modelCount": 31610, "officialConfigError": null, "officialConfigValid": true, - "successCount": 5772, - "successRate": 0.18269291637652718, - "wilsonLowerBound": 0.17847062032907862 + "successCount": 5782, + "successRate": 0.1829167984814932, + "wilsonLowerBound": 0.17869350910752324 } }, "Kunlunxin_p-800": { "vllm": { "framework": "vllm", - "modelCount": 61006, + "modelCount": 61010, "officialConfigError": null, "officialConfigValid": true, "successCount": 12400, - "successRate": 0.2032586958659804, - "wilsonLowerBound": 0.2000840287613424 + "successRate": 0.20324536961153908, + "wilsonLowerBound": 0.20007088477216128 }, "vllm_fix_tokenizer": { "framework": "vllm_fix_tokenizer", - "modelCount": 8840, + "modelCount": 8883, "officialConfigError": null, "officialConfigValid": true, - "successCount": 2563, - "successRate": 0.2899321266968326, - "wilsonLowerBound": 0.28056636484428565 + "successCount": 2572, + "successRate": 0.2895418214567151, + "wilsonLowerBound": 0.28020245558873214 }, "vllm_tokenizer_patch": { "framework": "vllm_tokenizer_patch", - "modelCount": 13415, + "modelCount": 13436, "officialConfigError": null, "officialConfigValid": true, - "successCount": 3426, - "successRate": 0.2553857622064853, - "wilsonLowerBound": 0.24807705272621616 + "successCount": 3431, + "successRate": 0.2553587377195594, + "wilsonLowerBound": 0.2480559502473149 } }, "MetaX_c-500": { "vllm": { "framework": "vllm", - "modelCount": 62239, + "modelCount": 62273, "officialConfigError": null, "officialConfigValid": true, - "successCount": 17050, - "successRate": 0.27394399010266873, - "wilsonLowerBound": 0.27045421114408397 + "successCount": 17062, + "successRate": 0.2739871212242866, + "wilsonLowerBound": 0.2704981168908029 }, "vllm_tokenizer_patch": { "framework": "vllm_tokenizer_patch", - "modelCount": 2, + "modelCount": 3, "officialConfigError": null, "officialConfigValid": true, - "successCount": 1, - "successRate": 0.5, - "wilsonLowerBound": 0.09452865480086611 + "successCount": 2, + "successRate": 0.6666666666666666, + "wilsonLowerBound": 0.20765495512648788 } }, "Mthreads_s4000": { "llamacpp": { "framework": "llamacpp", - "modelCount": 46859, + "modelCount": 46871, "officialConfigError": null, "officialConfigValid": true, - "successCount": 20582, - "successRate": 0.43923259139119486, - "wilsonLowerBound": 0.4347441147911954 + "successCount": 20593, + "successRate": 0.439354824945062, + "wilsonLowerBound": 0.4348667769133688 }, "vllm": { "framework": "vllm", - "modelCount": 37007, + "modelCount": 37028, "officialConfigError": null, "officialConfigValid": true, - "successCount": 3643, - "successRate": 0.09844083551760478, - "wilsonLowerBound": 0.09544710642113381 + "successCount": 3650, + "successRate": 0.09857405206870476, + "wilsonLowerBound": 0.0955793187698912 }, "vllm_tokenizer_patch": { "framework": "vllm_tokenizer_patch", @@ -336,12 +336,12 @@ }, "vllm_fix_tokenizer": { "framework": "vllm_fix_tokenizer", - "modelCount": 6112, + "modelCount": 6119, "officialConfigError": null, "officialConfigValid": true, - "successCount": 2607, - "successRate": 0.42653795811518325, - "wilsonLowerBound": 0.4141886567961639 + "successCount": 2611, + "successRate": 0.4267037097564962, + "wilsonLowerBound": 0.4143607238280708 } }, "Vastai_va16": { @@ -356,139 +356,139 @@ }, "vllm_fix_tokenizer": { "framework": "vllm_fix_tokenizer", - "modelCount": 12180, + "modelCount": 12193, "officialConfigError": null, "officialConfigValid": true, "successCount": 3897, - "successRate": 0.31995073891625614, - "wilsonLowerBound": 0.3117245426449319 + "successRate": 0.3196096120725006, + "wilsonLowerBound": 0.31139021690565494 } }, "hygon_k100-ai": { "llamacpp": { "framework": "llamacpp", - "modelCount": 26723, + "modelCount": 26731, "officialConfigError": null, "officialConfigValid": true, - "successCount": 13575, - "successRate": 0.5079893724506979, - "wilsonLowerBound": 0.5019944990717333 + "successCount": 13579, + "successRate": 0.5079869814073548, + "wilsonLowerBound": 0.501993005090935 }, "vllm": { "framework": "vllm", - "modelCount": 63221, + "modelCount": 63249, "officialConfigError": null, "officialConfigValid": true, - "successCount": 6420, - "successRate": 0.10154853608769238, - "wilsonLowerBound": 0.09921813466395533 + "successCount": 6423, + "successRate": 0.10155101266423185, + "wilsonLowerBound": 0.09922109618427101 }, "vllm-patch-tokenizer": { "framework": "vllm-patch-tokenizer", - "modelCount": 12673, + "modelCount": 12682, "officialConfigError": null, "officialConfigValid": true, - "successCount": 1852, - "successRate": 0.14613745758699598, - "wilsonLowerBound": 0.14009446290666172 + "successCount": 1855, + "successRate": 0.14627030436839616, + "wilsonLowerBound": 0.14022706216766626 } } } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-09-23T01:36:16.581766+00:00", + "generatedAt": "2026-09-23T01:39:44.904617+00:00", "gpuStats": { "Ascend_910-b4": { "available": true, - "backlogHours": 1254.9777777777779, + "backlogHours": 1293.3893129770993, "canVerify": true, "error": null, "gpu": "Ascend_910-b4", "healthFactor": 1.0, "maxConcurrentTasks": 8, - "qualityFactor": 1.9039851561039232, - "queueFactor": 0.959640851243542, - "queueWeight": 0.959640851243542, - "recentSuccess": 58, - "recentSuccessRate": 0.42962962962962964, - "recentTerminal": 135, - "recentWilsonLowerBound": 0.34921160149343466, - "running": 9, - "selectionWeight": 1.8271419359586372, + "qualityFactor": 1.9684796328019638, + "queueFactor": 0.9538962620750339, + "queueWeight": 0.9538962620750339, + "recentSuccess": 57, + "recentSuccessRate": 0.4351145038167939, + "recentTerminal": 131, + "recentWilsonLowerBound": 0.3532618019412418, + "running": 8, + "selectionWeight": 1.8777253637006286, "stale": false, "submissionEligible": true, - "throughputPerHour": 22.5, - "waiting": 28237 + "throughputPerHour": 21.833333333333332, + "waiting": 28239 }, "Biren_166m": { "available": true, - "backlogHours": 191.62025316455697, + "backlogHours": 185.52147239263803, "canVerify": true, "error": null, "gpu": "Biren_166m", "healthFactor": 1.0, "maxConcurrentTasks": 8, - "qualityFactor": 0.20056777661681796, - "queueFactor": 1.2721488252448303, - "queueWeight": 1.2721488252448303, - "recentSuccess": 28, - "recentSuccessRate": 0.17721518987341772, - "recentTerminal": 158, - "recentWilsonLowerBound": 0.12554945913041102, + "qualityFactor": 0.2067182248730712, + "queueFactor": 1.2764429524527203, + "queueWeight": 1.2764429524527203, + "recentSuccess": 29, + "recentSuccessRate": 0.17791411042944785, + "recentTerminal": 163, + "recentWilsonLowerBound": 0.12682630361869113, "running": 8, - "selectionWeight": 0.25515206140505253, + "selectionWeight": 0.26386402128276837, "stale": false, "submissionEligible": false, - "throughputPerHour": 26.333333333333332, - "waiting": 5046 + "throughputPerHour": 27.166666666666668, + "waiting": 5040 }, "Cambricon_mlu-370-x4": { "available": true, - "backlogHours": 1900.375, + "backlogHours": 1861.1020408163267, "canVerify": true, "error": null, "gpu": "Cambricon_mlu-370-x4", "healthFactor": 1.0, "maxConcurrentTasks": 7, - "qualityFactor": 0.7916049482162266, - "queueFactor": 0.9017335666091757, - "queueWeight": 0.9017335666091757, + "qualityFactor": 0.7602664847932732, + "queueFactor": 0.9032230442914669, + "queueWeight": 0.9032230442914669, "recentSuccess": 17, - "recentSuccessRate": 0.3541666666666667, - "recentTerminal": 48, - "recentWilsonLowerBound": 0.23433457112685732, + "recentSuccessRate": 0.3469387755102041, + "recentTerminal": 49, + "recentWilsonLowerBound": 0.22924209609314436, "running": 7, - "selectionWeight": 0.7138167533004899, + "selectionWeight": 0.6866902088677524, "stale": false, "submissionEligible": true, - "throughputPerHour": 8.0, - "waiting": 15203 + "throughputPerHour": 8.166666666666666, + "waiting": 15199 }, "Cambricon_mlu-370-x8": { "available": true, - "backlogHours": 447.0, + "backlogHours": 450.59504132231405, "canVerify": true, "error": null, "gpu": "Cambricon_mlu-370-x8", "healthFactor": 1.0, "maxConcurrentTasks": 7, - "qualityFactor": 0.26635569244272456, - "queueFactor": 1.1203610558719406, - "queueWeight": 1.1203610558719406, - "recentSuccess": 25, - "recentSuccessRate": 0.20491803278688525, - "recentTerminal": 122, - "recentWilsonLowerBound": 0.14282861339624775, + "qualityFactor": 0.24522885454580437, + "queueFactor": 1.1173585999624414, + "queueWeight": 1.1173585999624414, + "recentSuccess": 24, + "recentSuccessRate": 0.19834710743801653, + "recentTerminal": 121, + "recentWilsonLowerBound": 0.13706713532662643, "running": 7, - "selectionWeight": 0.29841454482263274, + "selectionWeight": 0.27400856958569314, "stale": false, "submissionEligible": false, - "throughputPerHour": 20.333333333333332, - "waiting": 9089 + "throughputPerHour": 20.166666666666668, + "waiting": 9087 }, "Iluvatar_bi-100": { "available": true, - "backlogHours": 44.38871473354232, + "backlogHours": 43.02127659574468, "canVerify": true, "error": null, "gpu": "Iluvatar_bi-100", @@ -497,20 +497,20 @@ "qualityFactor": 0.05, "queueFactor": 1.3, "queueWeight": 1.3, - "recentSuccess": 3, - "recentSuccessRate": 0.009404388714733543, - "recentTerminal": 319, - "recentWilsonLowerBound": 0.0032033371501954864, + "recentSuccess": 4, + "recentSuccessRate": 0.0121580547112462, + "recentTerminal": 329, + "recentWilsonLowerBound": 0.004737834320151895, "running": 24, "selectionWeight": 0.065, "stale": false, "submissionEligible": false, - "throughputPerHour": 53.166666666666664, - "waiting": 2360 + "throughputPerHour": 54.833333333333336, + "waiting": 2359 }, "Iluvatar_bi-150": { "available": true, - "backlogHours": 135.77777777777777, + "backlogHours": 136.07441860465116, "canVerify": true, "error": null, "gpu": "Iluvatar_bi-150", @@ -520,174 +520,174 @@ "queueFactor": 1.3, "queueWeight": 1.3, "recentSuccess": 9, - "recentSuccessRate": 0.041666666666666664, - "recentTerminal": 216, - "recentWilsonLowerBound": 0.02207308242564397, - "running": 1, + "recentSuccessRate": 0.04186046511627907, + "recentTerminal": 215, + "recentWilsonLowerBound": 0.02217646863045342, + "running": 6, "selectionWeight": 0.065, "stale": false, "submissionEligible": false, - "throughputPerHour": 36.0, - "waiting": 4888 + "throughputPerHour": 35.833333333333336, + "waiting": 4876 }, "Iluvatar_mrv-100": { "available": true, - "backlogHours": 2660.1666666666665, + "backlogHours": 2588.27027027027, "canVerify": true, "error": null, "gpu": "Iluvatar_mrv-100", "healthFactor": 1.0, "maxConcurrentTasks": 2, - "qualityFactor": 0.5719045492896547, - "queueFactor": 0.8573690571748939, - "queueWeight": 0.8573690571748939, - "recentSuccess": 12, - "recentSuccessRate": 0.3333333333333333, - "recentTerminal": 36, - "recentWilsonLowerBound": 0.20214424774586046, + "qualityFactor": 0.6823942934010339, + "queueFactor": 0.8596251113461741, + "queueWeight": 0.8596251113461741, + "recentSuccess": 13, + "recentSuccessRate": 0.35135135135135137, + "recentTerminal": 37, + "recentWilsonLowerBound": 0.21825406631100872, "running": 2, - "selectionWeight": 0.4903332642185039, + "selectionWeight": 0.5866032704468576, "stale": false, "submissionEligible": true, - "throughputPerHour": 6.0, + "throughputPerHour": 6.166666666666667, "waiting": 15961 }, "Kunlunxin_p-800": { "available": true, - "backlogHours": 442.0851063829787, + "backlogHours": 438.4225352112676, "canVerify": true, "error": null, "gpu": "Kunlunxin_p-800", "healthFactor": 1.0, "maxConcurrentTasks": 8, - "qualityFactor": 0.33926392256384197, - "queueFactor": 1.122220634911549, - "queueWeight": 1.122220634911549, + "qualityFactor": 0.3365313843857509, + "queueFactor": 1.1219580186675209, + "queueWeight": 1.1219580186675209, "recentSuccess": 31, - "recentSuccessRate": 0.2198581560283688, - "recentTerminal": 141, - "recentWilsonLowerBound": 0.15943251615033457, + "recentSuccessRate": 0.21830985915492956, + "recentTerminal": 142, + "recentWilsonLowerBound": 0.158275038652959, "running": 8, - "selectionWeight": 0.38072897458217736, + "selectionWeight": 0.37757408524487496, "stale": false, "submissionEligible": true, - "throughputPerHour": 23.5, - "waiting": 10389 + "throughputPerHour": 23.666666666666668, + "waiting": 10376 }, "MetaX_c-500": { "available": true, - "backlogHours": 498.276923076923, + "backlogHours": 505.59375, "canVerify": true, "error": null, "gpu": "MetaX_c-500", "healthFactor": 1.0, "maxConcurrentTasks": 4, - "qualityFactor": 0.31179789350819875, - "queueFactor": 1.1022586523330895, - "queueWeight": 1.1022586523330895, + "qualityFactor": 0.32554102316277633, + "queueFactor": 1.0982223623066294, + "queueWeight": 1.0982223623066294, "recentSuccess": 28, - "recentSuccessRate": 0.2153846153846154, - "recentTerminal": 130, - "recentWilsonLowerBound": 0.15343032935030532, + "recentSuccessRate": 0.21875, + "recentTerminal": 128, + "recentWilsonLowerBound": 0.1559042491230976, "running": 5, - "selectionWeight": 0.3436819258986433, + "selectionWeight": 0.3575164314855414, "stale": false, "submissionEligible": true, - "throughputPerHour": 21.666666666666668, - "waiting": 10796 + "throughputPerHour": 21.333333333333332, + "waiting": 10786 }, "Mthreads_s4000": { "available": true, - "backlogHours": 2365.0588235294117, + "backlogHours": 2461.469387755102, "canVerify": true, "error": null, "gpu": "Mthreads_s4000", "healthFactor": 1.0, "maxConcurrentTasks": 4, "qualityFactor": 2.5, - "queueFactor": 0.8726253809729951, - "queueWeight": 0.8726253809729951, - "recentSuccess": 27, - "recentSuccessRate": 0.5294117647058824, - "recentTerminal": 51, - "recentWilsonLowerBound": 0.39523071344726596, + "queueFactor": 0.8661265894758311, + "queueWeight": 0.8661265894758311, + "recentSuccess": 26, + "recentSuccessRate": 0.5306122448979592, + "recentTerminal": 49, + "recentWilsonLowerBound": 0.3938062701991985, "running": 4, - "selectionWeight": 2.1815634524324876, + "selectionWeight": 2.1653164736895776, "stale": false, "submissionEligible": true, - "throughputPerHour": 8.5, - "waiting": 20103 + "throughputPerHour": 8.166666666666666, + "waiting": 20102 }, "Sunrise_pt-200-x1": { "available": true, - "backlogHours": 7298.769230769231, + "backlogHours": 7299.6923076923085, "canVerify": true, "error": null, "gpu": "Sunrise_pt-200-x1", "healthFactor": 1.0, "maxConcurrentTasks": 2, - "qualityFactor": 1.2789631739021758, - "queueFactor": 0.7369137970432916, - "queueWeight": 0.7369137970432916, + "qualityFactor": 1.2891628172601364, + "queueFactor": 0.7358085907693738, + "queueWeight": 0.7358085907693738, "recentSuccess": 7, "recentSuccessRate": 0.5384615384615384, "recentTerminal": 13, "recentWilsonLowerBound": 0.29143432431832045, "running": 2, - "selectionWeight": 0.9424856087587921, + "selectionWeight": 0.9485770758404567, "stale": false, "submissionEligible": false, "throughputPerHour": 2.1666666666666665, - "waiting": 15814 + "waiting": 15816 }, "Vastai_va16": { "available": true, - "backlogHours": 3511.4399999999996, + "backlogHours": 3378.0000000000005, "canVerify": true, "error": null, "gpu": "Vastai_va16", "healthFactor": 1.0, "maxConcurrentTasks": 16, "qualityFactor": 0.05, - "queueFactor": 0.8223966732616653, - "queueWeight": 0.8223966732616653, + "queueFactor": 0.8259648968879385, + "queueWeight": 0.8259648968879385, "recentSuccess": 0, "recentSuccessRate": 0.0, - "recentTerminal": 25, + "recentTerminal": 26, "recentWilsonLowerBound": 0.0, "running": 16, - "selectionWeight": 0.04111983366308327, + "selectionWeight": 0.041298244844396925, "stale": false, "submissionEligible": false, - "throughputPerHour": 4.166666666666667, - "waiting": 14631 + "throughputPerHour": 4.333333333333333, + "waiting": 14638 }, "hygon_k100-ai": { "available": true, - "backlogHours": 953.5882352941177, + "backlogHours": 944.2135922330096, "canVerify": true, "error": null, "gpu": "hygon_k100-ai", "healthFactor": 1.0, "maxConcurrentTasks": 6, - "qualityFactor": 0.4446668366328316, + "qualityFactor": 0.39458828613098623, "queueFactor": 1.0, "queueWeight": 1.0, - "recentSuccess": 26, - "recentSuccessRate": 0.2549019607843137, - "recentTerminal": 102, - "recentWilsonLowerBound": 0.1802954037747794, + "recentSuccess": 25, + "recentSuccessRate": 0.24271844660194175, + "recentTerminal": 103, + "recentWilsonLowerBound": 0.17014922730424603, "running": 6, - "selectionWeight": 0.4446668366328316, + "selectionWeight": 0.39458828613098623, "stale": false, "submissionEligible": true, - "throughputPerHour": 17.0, - "waiting": 16211 + "throughputPerHour": 17.166666666666668, + "waiting": 16209 } }, - "queueAttemptedAt": "2026-09-23T01:29:32.152287+00:00", + "queueAttemptedAt": "2026-09-23T01:39:44.904617+00:00", "queueError": null, - "queueUpdatedAt": "2026-09-23T01:29:32.152287+00:00", + "queueUpdatedAt": "2026-09-23T01:39:44.904617+00:00", "supportedGpus": [ "Vastai_va16", "Cambricon_mlu-370-x4", diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 71da9a2e9..63eb20f6c 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-09-23T01:36:16.581766+00:00", + "catalogUpdatedAt": "2026-09-23T01:39:44.904617+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-09-23T01:36:16.581766+00:00", + "generatedAt": "2026-09-23T01:39:44.904617+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6669,6 +6669,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-09-23T01:36:16.581766+00:00", + "taskTreeUpdatedAt": "2026-09-23T01:39:44.904617+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 730f90154..ed0a1715c 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-09-23T01:33:35.419411+00:00", - "lastSyncTime": "2026-09-23T01:33:35.361109+00:00", + "generatedAt": "2026-09-23T01:38:35.390807+00:00", + "lastSyncTime": "2026-09-23T01:38:33.278599+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -4681,10 +4681,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 127, + "ambiguous_runtime": 128, "参数/模板问题": 3 }, - "failureCount": 130, + "failureCount": 131, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, @@ -4694,8 +4694,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 130, - "unresolvedFailureCount": 130 + "total": 131, + "unresolvedFailureCount": 131 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 39, @@ -5838,7 +5838,7 @@ "decisionSuccessRate": 0.036, "decisionTotal": 139, "failureBreakdown": { - "ambiguous_runtime": 296, + "ambiguous_runtime": 297, "backend_operator": 8, "framework_architecture_unsupported": 29, "memory_capacity": 10, @@ -5847,15 +5847,15 @@ "tokenizer_compatibility": 82, "参数/模板问题": 13 }, - "failureCount": 460, - "failureRate": 0.9892, + "failureCount": 461, + "failureRate": 0.9893, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 17, "successCount": 5, - "successRate": 0.0108, - "total": 465, - "unresolvedFailureCount": 309 + "successRate": 0.0107, + "total": 466, + "unresolvedFailureCount": 310 }, "vllm_tokenizer_patch": { "attributableFailureCount": 106, @@ -5886,7 +5886,7 @@ "unresolvedFailureCount": 173 } }, - "generatedAt": "2026-09-23T01:33:35.406215+00:00", + "generatedAt": "2026-09-23T01:38:35.380411+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 102, @@ -6117,7 +6117,7 @@ "decisionSuccessRate": 0.0893, "decisionTotal": 56, "failureBreakdown": { - "ambiguous_runtime": 208, + "ambiguous_runtime": 209, "backend_operator": 10, "framework_architecture_unsupported": 23, "memory_capacity": 2, @@ -6129,15 +6129,15 @@ "日志缺失": 1, "验证失败": 23 }, - "failureCount": 316, - "failureRate": 0.9844, + "failureCount": 317, + "failureRate": 0.9845, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 5, - "successRate": 0.0156, - "total": 321, - "unresolvedFailureCount": 264 + "successRate": 0.0155, + "total": 322, + "unresolvedFailureCount": 265 }, "Kunlunxin_r-200-8f": { "attributableFailureCount": 0, @@ -16343,9 +16343,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 4 + "ambiguous_runtime": 5 }, - "failureCount": 4, + "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "phi3", @@ -16357,8 +16357,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 4, - "unresolvedFailureCount": 4 + "total": 5, + "unresolvedFailureCount": 5 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|none": { "attributableFailureCount": 0, @@ -39193,9 +39193,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 2 + "ambiguous_runtime": 3 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, @@ -39208,8 +39208,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 3, + "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|none|31": { "attributableFailureCount": 0, @@ -45609,15 +45609,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 16785, - "totalRecords": 17003, + "terminalRecords": 16786, + "totalRecords": 17004, "totals": { "attributableFailureCount": 6009, "decisionFailureRate": 0.8621, "decisionSuccessRate": 0.1379, "decisionTotal": 6970, "failureBreakdown": { - "ambiguous_runtime": 4278, + "ambiguous_runtime": 4279, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 113, @@ -45633,71 +45633,71 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 15824, + "failureCount": 15825, "failureRate": 0.9427, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 929, "successCount": 961, "successRate": 0.0573, - "total": 16785, - "unresolvedFailureCount": 8886 + "total": 16786, + "unresolvedFailureCount": 8887 }, "warnings": [ - "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", - "组合 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 hygon_k100-ai|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Sunrise_pt-200-x1|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "组合 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 hygon_k100-ai|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-150|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Sunrise_pt-200-x1|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 MetaX_c-500|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" + "组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" ] }, "storageMode": "decision_state_only", - "summarizedRecords": 17003, + "summarizedRecords": 17004, "version": 1 } diff --git a/.modelhub_state/queue_cleanup_latest.json b/.modelhub_state/queue_cleanup_latest.json index 03b7f7eac..b05530ad8 100644 --- a/.modelhub_state/queue_cleanup_latest.json +++ b/.modelhub_state/queue_cleanup_latest.json @@ -14,7 +14,7 @@ 100 ], "accounts": 12, - "activeScanned": 1064, + "activeScanned": 1054, "ageCleanupMode": "admission_only", "agePolicySkipped": { "cleanupDisabled": true, @@ -38,11 +38,27 @@ "vllm_fix_tokenizer", "vllm_tokenizer_patch" ], + "cambricon_mlu-370-x4|text-generation": [ + "vllm", + "vllm-customized", + "vllm-mlu" + ], + "cambricon_mlu-370-x8|text-generation": [ + "vllm", + "vllm-customized", + "vllm-mlu" + ], "hygon_k100-ai|text-generation": [ "llamacpp", "vllm", "vllm-patch-tokenizer" ], + "iluvatar_bi-100|text-generation": [ + "transformers", + "vllm", + "vllm-patch-tokenizer", + "vllm_fix_tokenizer" + ], "iluvatar_bi-150|text-generation": [ "llamacpp", "transformers", @@ -51,11 +67,19 @@ "vllm_fix_tokenizer", "vllm_tokenizer_patch" ], + "iluvatar_mrv-100|text-generation": [ + "transformers", + "vllm" + ], "kunlunxin_p-800|text-generation": [ "vllm", "vllm_fix_tokenizer", "vllm_tokenizer_patch" ], + "metax_c-500|text-generation": [ + "vllm", + "vllm_tokenizer_patch" + ], "mthreads_s4000|text-generation": [ "llamacpp", "vllm", @@ -65,222 +89,15 @@ "sglang", "vllm", "vllm_fix_tokenizer" + ], + "vastai_va16|text-generation": [ + "vllm", + "vllm_fix_tokenizer" ] }, "architectureFrameworkCatalogErrors": {}, - "architectureIncompatibleCount": 10, - "architectureIncompatibleTasks": [ - { - "accountIndex": 1, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4985113, - "taskType": "text-generation" - }, - { - "accountIndex": 1, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4987156, - "taskType": "text-generation" - }, - { - "accountIndex": 2, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4992046, - "taskType": "text-generation" - }, - { - "accountIndex": 5, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4987155, - "taskType": "text-generation" - }, - { - "accountIndex": 5, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4987486, - "taskType": "text-generation" - }, - { - "accountIndex": 9, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 5001319, - "taskType": "text-generation" - }, - { - "accountIndex": 10, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4984931, - "taskType": "text-generation" - }, - { - "accountIndex": 10, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4986237, - "taskType": "text-generation" - }, - { - "accountIndex": 11, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4984928, - "taskType": "text-generation" - }, - { - "accountIndex": 11, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4996858, - "taskType": "text-generation" - } - ], + "architectureIncompatibleCount": 0, + "architectureIncompatibleTasks": [], "architectureModelConfigErrors": { "GestaltLabs/Ornstein-3.5-9B-V2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/GestaltLabs/Ornstein-3.5-9B-V2-GGUF/resolve/master/config.json (status=404)", "LiquidAI/LFM2.5-2.6B-DSpark-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B-DSpark-GGUF/resolve/master/config.json (status=500)", @@ -304,7 +121,7 @@ "z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)" }, "architectureModelConfigsComplete": 53, - "architectureOnly": true, + "architectureOnly": false, "architecturePolicySkipped": { "frameworkCatalogUnknown": 0, "frameworkContextUnknown": 59, @@ -315,252 +132,11 @@ "submissionContextMismatch": 0, "submissionContextUnknown": 0 }, - "cancelledCount": 10, - "cancelledTasks": [ - { - "accountIndex": 1, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "cleanupReasons": [ - "known_framework_architecture_incompatible" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4985113, - "taskType": "text-generation" - }, - { - "accountIndex": 1, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "cleanupReasons": [ - "known_framework_architecture_incompatible" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4987156, - "taskType": "text-generation" - }, - { - "accountIndex": 2, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "cleanupReasons": [ - "known_framework_architecture_incompatible" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4992046, - "taskType": "text-generation" - }, - { - "accountIndex": 5, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "cleanupReasons": [ - "known_framework_architecture_incompatible" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4987155, - "taskType": "text-generation" - }, - { - "accountIndex": 5, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "cleanupReasons": [ - "known_framework_architecture_incompatible" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4987486, - "taskType": "text-generation" - }, - { - "accountIndex": 9, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "cleanupReasons": [ - "known_framework_architecture_incompatible" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 5001319, - "taskType": "text-generation" - }, - { - "accountIndex": 10, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "cleanupReasons": [ - "known_framework_architecture_incompatible" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4984931, - "taskType": "text-generation" - }, - { - "accountIndex": 10, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "cleanupReasons": [ - "known_framework_architecture_incompatible" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4986237, - "taskType": "text-generation" - }, - { - "accountIndex": 11, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "cleanupReasons": [ - "known_framework_architecture_incompatible" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4984928, - "taskType": "text-generation" - }, - { - "accountIndex": 11, - "architectureBlockEvidenceCount": 1, - "architectureBlockExpiresAt": "2026-10-20T20:51:02.374696+00:00", - "architectureMatchScope": "exact_framework", - "architectureMatchType": "model_type", - "architectureSignature": "model_type:qwen3_5", - "architectureSignatures": [ - "model_type:qwen3_5" - ], - "cleanupReasons": [ - "known_framework_architecture_incompatible" - ], - "evaluatedFrameworks": [ - "vllm" - ], - "framework": "vllm", - "gpuType": "Kunlunxin_p-800", - "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", - "reason": "known_framework_architecture_incompatible", - "status": "waiting", - "taskId": 4996858, - "taskType": "text-generation" - } - ], + "cancelledCount": 0, + "cancelledTasks": [], "certainOomCount": 0, "certainOomTasks": [], - "cleanupCandidateCount": 10, + "cleanupCandidateCount": 0, "dryRun": false, "listingErrors": {}, "modelAgeErrors": {}, @@ -585,18 +161,20 @@ ], "oldOverflowCount": 0, "oldOverflowTasks": [], - "policyCancelledRecorded": 10, + "policyCancelledRecorded": 0, "policyNoLongerAppliesCount": 0, "policyNoLongerAppliesTasks": [], "recentModelDays": 7, "recentModelReserveSlots": 5, - "repositorySizeErrors": {}, - "repositorySizesComplete": 0, + "repositorySizeErrors": { + "empero-ai/Qwen3.8-9B-GGUF": "recursive_repository_size_incomplete" + }, + "repositorySizesComplete": 368, "skipped": { - "fitsKnownCapacity": 0, + "fitsKnownCapacity": 1052, "gpuCapacityUnknown": 0, - "repositorySizeUnknown": 0 + "repositorySizeUnknown": 2 }, "stopErrors": [], - "uniqueModels": 372 + "uniqueModels": 369 } diff --git a/manifest.json b/manifest.json index 0eb8b1137..9becd32d2 100644 --- a/manifest.json +++ b/manifest.json @@ -2,12 +2,12 @@ "agentVersion": "2026.09.22.1", "checksums": { ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", - ".modelhub_state/architecture_compatibility_blacklist.json": "d5ef243efbf030d0f0747de28019e510a79a8eda76bde9b02e56634bb5e7ee85", + ".modelhub_state/architecture_compatibility_blacklist.json": "8674dd0d0e04e7584bcfe02b0133e2658a2ea4c8a6bf3ab2e998980c686cf994", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "f645833abe20861d1249e9b62af566cff4c382686e77fc89cd5a76fb4b8caa87", - ".modelhub_state/official_capabilities.json": "65a672534f962064f4906117ab5c0bce4a92a6ab4ee2128992e3f13932ffdaf6", - ".modelhub_state/outcome_checkpoint.json": "32ebfda4abfab6052679b0c6705844014cca32681f126bde621babf6ffed0741", - ".modelhub_state/queue_cleanup_latest.json": "25b072614686a8dea931431bf7c311a7f76d027c8b4f273ae90a556d9345992d", + ".modelhub_state/market_intelligence.json": "b2f70aae0cfed5aa2372db49a8a3386f88225be2f1d31ee9aba17c6c3328e0cc", + ".modelhub_state/official_capabilities.json": "5e7885c72c4513fc4db27462f84628901d960236eb34dd5c5cbcd2484d830d71", + ".modelhub_state/outcome_checkpoint.json": "2d951941100ab7ea30decc4a7a9021e778769d05af894b55503267930a17fef0", + ".modelhub_state/queue_cleanup_latest.json": "abeedea8ce654c253250bcfd506d9b5eab392b53faf9867483b77b9a5c85233b", ".modelhub_state/recent_outcomes.jsonl": "6684cca26023ab1863cd968bfbdd817493550ff274926a22a77747d93b7f5b95", ".modelhub_state/recovery_active_tasks.jsonl": "0ddbab9c9eebf724015399669d0e8a8afdb35bcc0271dc83ca3c96821138096c", ".modelhub_state/recovery_intents.jsonl": "3491ba145f599fed8aa545307d6262a32593c32412076f328c342e84d364e0df", @@ -15,11 +15,11 @@ ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "619eac16f716b2420672872ff4ce92d452f5fced4f96e8dbb37f9ce511b53c5b", "ledger/submissions.jsonl": "dae1e070159c8b2cae2773baa1f8f13efb2ee673e6d099ad54449477fb3fd09a", - "outcomes/submissions.jsonl": "4f815c14602cb1af5c01ec33d4f8c47f96bf9d2e9ad12dcbf185be0d1ae4a94a" + "outcomes/submissions.jsonl": "68fdd20a64905c76457bb448a0dee096150e282e0858edfc86eaa96954b5f080" }, - "generation": 13256, - "phase": "startup", + "generation": 13257, + "phase": "cycle", "schemaVersion": 1, - "updatedAt": "2026-09-23T01:38:32.280788+00:00", + "updatedAt": "2026-09-23T01:40:43.815359+00:00", "writerId": "328f98096427428498653b568f0d5041" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index bec1ad197..fb019b29a 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -439,7 +439,6 @@ {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:21:49.901792+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.933362+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970576", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901937+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663548868, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663548868}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.792755+00:00", "targetGpu": "Vastai_va16", "taskId": "4970571", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901659+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72670025872, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679340864, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int88", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679340864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.788367+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970568", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901932+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.920885+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970573", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:21:49.901883+00:00", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673858, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860673858}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.922099+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970574", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:21:49.902090+00:00", "modelId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256941144}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.856488+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970570", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901716+00:00", "modelId": "LiquidAI/LFM2.5-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427456, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412393192, "modelscopeLicense": "other", "modelscopeParams": 2697198592, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412393192}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:41.844966+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970589", "taskType": "text-generation", "verifyResult": null}