state: generation 21146 (cycle)
This commit is contained in:
@@ -2872,7 +2872,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-05T23:08:08.658485+00:00",
|
||||
"generatedAt": "2026-10-05T23:19:03.698677+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 145,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-05T23:18:01.182853+00:00",
|
||||
"generatedAt": "2026-10-05T23:20:20.069104+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-10-05T23:18:01.182853+00:00",
|
||||
"catalogUpdatedAt": "2026-10-05T23:20:20.069104+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-10-05T23:18:01.182853+00:00",
|
||||
"generatedAt": "2026-10-05T23:20:20.069104+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6494,6 +6494,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-10-05T23:18:01.182853+00:00",
|
||||
"taskTreeUpdatedAt": "2026-10-05T23:20:20.069104+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-05T20:21:24.999460+00:00",
|
||||
"lastSyncTime": "2026-10-05T20:21:24.759390+00:00",
|
||||
"generatedAt": "2026-10-05T23:19:03.617409+00:00",
|
||||
"lastSyncTime": "2026-10-05T23:19:03.366027+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2355,25 +2355,6 @@
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"mthreads_s4000|vllm|text-generation|model_type:qwen3_5_text": {
|
||||
"architectureSignature": "model_type:qwen3_5_text",
|
||||
"architectures": [],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-05T21:33:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-05T21:33:21+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5_text",
|
||||
"sourceModelIds": [
|
||||
"SupraLabs/reasoning-summarizer-800m-pre"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4609104"
|
||||
],
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"mthreads_s4000|vllm|text-generation|model_type:qwen3_vl": {
|
||||
"architectureSignature": "model_type:qwen3_vl",
|
||||
"architectures": [],
|
||||
@@ -2896,7 +2877,7 @@
|
||||
}
|
||||
},
|
||||
"architectureCompatibilitySummary": {
|
||||
"activeBlockCount": 146,
|
||||
"activeBlockCount": 145,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 9,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 7,
|
||||
@@ -2915,7 +2896,7 @@
|
||||
"Kunlunxin_p-800|vllm": 10,
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch": 9,
|
||||
"MetaX_c-500|vllm": 3,
|
||||
"Mthreads_s4000|vllm": 8,
|
||||
"Mthreads_s4000|vllm": 7,
|
||||
"Sunrise_pt-200-x1|vllm": 3,
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
|
||||
"Vastai_va16|vllm": 15,
|
||||
@@ -4940,15 +4921,15 @@
|
||||
"unresolvedFailureCount": 158
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation": {
|
||||
"attributableFailureCount": 79,
|
||||
"decisionFailureRate": 0.767,
|
||||
"decisionSuccessRate": 0.233,
|
||||
"decisionTotal": 103,
|
||||
"attributableFailureCount": 80,
|
||||
"decisionFailureRate": 0.7692,
|
||||
"decisionSuccessRate": 0.2308,
|
||||
"decisionTotal": 104,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 78,
|
||||
"attention_backend": 2,
|
||||
"backend_operator": 8,
|
||||
"framework_architecture_unsupported": 56,
|
||||
"framework_architecture_unsupported": 57,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -4957,17 +4938,17 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 12
|
||||
},
|
||||
"failureCount": 170,
|
||||
"failureRate": 0.8763,
|
||||
"failureCount": 171,
|
||||
"failureRate": 0.8769,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 24,
|
||||
"successRate": 0.1237,
|
||||
"successRate": 0.1231,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 194,
|
||||
"total": 195,
|
||||
"unresolvedFailureCount": 90
|
||||
},
|
||||
"Mthreads_s4000|vllm|visual-multi-modal": {
|
||||
@@ -5593,17 +5574,17 @@
|
||||
"unresolvedFailureCount": 6477
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3663,
|
||||
"attributableFailureCount": 3664,
|
||||
"decisionFailureRate": 0.9721,
|
||||
"decisionSuccessRate": 0.0279,
|
||||
"decisionTotal": 3768,
|
||||
"decisionTotal": 3769,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1599,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 94,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1385,
|
||||
"framework_architecture_unsupported": 1386,
|
||||
"memory_capacity": 725,
|
||||
"model_load": 227,
|
||||
"platform_infrastructure": 878,
|
||||
@@ -5612,14 +5593,14 @@
|
||||
"tokenizer_compatibility": 420,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6190,
|
||||
"failureCount": 6191,
|
||||
"failureRate": 0.9833,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 878,
|
||||
"successCount": 105,
|
||||
"successRate": 0.0167,
|
||||
"total": 6295,
|
||||
"total": 6296,
|
||||
"unresolvedFailureCount": 1649
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -5770,7 +5751,7 @@
|
||||
"unresolvedFailureCount": 233
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-05T20:21:24.986276+00:00",
|
||||
"generatedAt": "2026-10-05T23:19:03.603262+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 119,
|
||||
@@ -6076,15 +6057,15 @@
|
||||
"unresolvedFailureCount": 766
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"attributableFailureCount": 83,
|
||||
"decisionFailureRate": 0.6484,
|
||||
"decisionSuccessRate": 0.3516,
|
||||
"decisionTotal": 128,
|
||||
"attributableFailureCount": 84,
|
||||
"decisionFailureRate": 0.6512,
|
||||
"decisionSuccessRate": 0.3488,
|
||||
"decisionTotal": 129,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 124,
|
||||
"attention_backend": 2,
|
||||
"backend_operator": 8,
|
||||
"framework_architecture_unsupported": 57,
|
||||
"framework_architecture_unsupported": 58,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 6,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -6095,14 +6076,14 @@
|
||||
"日志缺失": 96,
|
||||
"验证失败": 26
|
||||
},
|
||||
"failureCount": 386,
|
||||
"failureRate": 0.8956,
|
||||
"failureCount": 387,
|
||||
"failureRate": 0.8958,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 45,
|
||||
"successRate": 0.1044,
|
||||
"total": 431,
|
||||
"successRate": 0.1042,
|
||||
"total": 432,
|
||||
"unresolvedFailureCount": 302
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
@@ -21405,6 +21386,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|gemma4_unified|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "gemma4_unified",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|gemma4|none": {
|
||||
"attributableFailureCount": 3,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -52148,6 +52152,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|gemma4_unified|compressed-tensors|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "gemma4_unified",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|gemma4|none|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -57279,20 +57307,20 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17326,
|
||||
"totalRecords": 17550,
|
||||
"terminalRecords": 17327,
|
||||
"totalRecords": 17551,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6228,
|
||||
"attributableFailureCount": 6229,
|
||||
"decisionFailureRate": 0.8643,
|
||||
"decisionSuccessRate": 0.1357,
|
||||
"decisionTotal": 7206,
|
||||
"decisionTotal": 7207,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4541,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 129,
|
||||
"context_length": 327,
|
||||
"framework_architecture_unsupported": 2255,
|
||||
"framework_architecture_unsupported": 2256,
|
||||
"memory_capacity": 1206,
|
||||
"model_load": 565,
|
||||
"platform_infrastructure": 951,
|
||||
@@ -57303,14 +57331,14 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16348,
|
||||
"failureCount": 16349,
|
||||
"failureRate": 0.9436,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 951,
|
||||
"successCount": 978,
|
||||
"successRate": 0.0564,
|
||||
"total": 17326,
|
||||
"total": 17327,
|
||||
"unresolvedFailureCount": 9169
|
||||
},
|
||||
"warnings": [
|
||||
@@ -57338,7 +57366,7 @@
|
||||
"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-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 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 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 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 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_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 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。",
|
||||
@@ -57367,10 +57395,10 @@
|
||||
"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_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|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 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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17550,
|
||||
"summarizedRecords": 17551,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.22.1",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "2213acf2438d4c42df8151efede2310e8ca48806e0ce2ac026984a5aab10f339",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "bbcdc5fdb7485e2c4f58f565b7e919a2b859f4b0221cea62f77cb158b5606a36",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "449609c44791b67f5f33521706ef35a7973118ea6703c44011f2fb551cc7252f",
|
||||
".modelhub_state/official_capabilities.json": "01306a142d175e385657f5f9a6df4ed9a239997de9cb837bbb56e44dc6c3b653",
|
||||
".modelhub_state/outcome_checkpoint.json": "b8143b80431282844fb3ab638de92df5bb4b7d6b68aa7ec04426257e4e0ea1e6",
|
||||
".modelhub_state/market_intelligence.json": "80ecc04c69d743b1f9a0f66bd017f3c2da3c79d79941586c57dcb52ce150a53a",
|
||||
".modelhub_state/official_capabilities.json": "0edccd0384196a7af4942bc1525083f104f8a8f3b4362679ec1538e7846f917c",
|
||||
".modelhub_state/outcome_checkpoint.json": "a70fa8c0e1fa2ed34193f1bd4c0fbbd6b0f15af556f9288a81cc9e0af6e021c3",
|
||||
".modelhub_state/queue_cleanup_latest.json": "37a92df5dbd2c6d207e323031242f864be96827043ca583084769f1f466765cb",
|
||||
".modelhub_state/recent_outcomes.jsonl": "66f65405defcf850f044e43e54c3dc291f18521f309cb9962d861b493cb049ac",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "ff567033c0cf5c4507eac5aabcb16c16de48525dac8f1adf63fb34962afc9937",
|
||||
".modelhub_state/recovery_intents.jsonl": "941a0aad32054e14f2d1bb10ccef241bdce70bf42c645abe0d701560dd74916e",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "eb74aa574b1bd680093baf365073f78de1c0b2a4798346a4f14f2356df668085",
|
||||
".modelhub_state/recovery_intents.jsonl": "304116daf4d11d3064e5b587a72cc6b8625107f594410364fbf15dc6159b9852",
|
||||
".modelhub_state/routing_intelligence.json": "fd679e61008e930cca88ce220ce5fcded760a926d2391985ac149cdba5cdec55",
|
||||
".modelhub_state/submission_exclusions.jsonl": "8a533753b09639322718ffe59fad6a6f11e8cc3741d7be12085a149c97ca5507",
|
||||
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
|
||||
"ledger/submissions.jsonl": "88fd4a8d6fb4e12230bca0c97bd9a0db370e50b25e0b34a627851aa4a419b7a0",
|
||||
"outcomes/submissions.jsonl": "8663f88f724c1acef8b730f5b77cb0b614e73553ac60d1b2f918c21370973658"
|
||||
"outcomes/submissions.jsonl": "95400e88752a3d6d837255e8b83b62ecb41eab19c3792aed2871174737be8103"
|
||||
},
|
||||
"generation": 21145,
|
||||
"generation": 21146,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-10-05T23:18:02.033726+00:00",
|
||||
"updatedAt": "2026-10-05T23:20:26.421587+00:00",
|
||||
"writerId": "c99196ebc91b43dbbcacb4830cce7e56"
|
||||
}
|
||||
|
||||
@@ -158,7 +158,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671248+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:53:59.224352+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970246", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.670810+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "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": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:53:59.235830+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970247", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.671236+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:58:35.447710+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970349", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671020+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:58:41.296912+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970360", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901858+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:10:03.058495+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970512", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901772+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "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": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:11:06.683086+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970527", "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}
|
||||
|
||||
Reference in New Issue
Block a user