state: generation 4888 (cycle)

This commit is contained in:
2026-09-10 01:44:14 +00:00
parent 0e12ba6ba9
commit 0ae011cf21
10 changed files with 1940 additions and 1918 deletions

View File

@@ -1306,7 +1306,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T01:41:34.057134+00:00",
"generatedAt": "2026-09-10T01:44:13.288789+00:00",
"summary": {
"activeBlockCount": 65,
"byGpuFramework": {

View File

@@ -19,7 +19,7 @@
"10": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 347,
"listingErrors": 348,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 10,
"nextAccountIndex": 11,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T01:41:34.033246+00:00",
"updatedAt": "2026-09-10T01:44:13.265405+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T01:40:06.373893+00:00",
"generatedAt": "2026-09-10T01:42:43.728821+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T01:16:26.316475+00:00",
"lastSyncTime": "2026-09-10T01:16:26.008867+00:00",
"generatedAt": "2026-09-10T01:42:35.052275+00:00",
"lastSyncTime": "2026-09-10T01:42:34.770281+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1565,25 +1565,25 @@
"decisionSuccessRate": 0.2222,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 5,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 5,
"验证失败": 22
},
"failureCount": 44,
"failureRate": 0.9565,
"failureCount": 45,
"failureRate": 0.9574,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0435,
"successRate": 0.0426,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 46,
"unresolvedFailureCount": 37
"total": 47,
"unresolvedFailureCount": 38
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 7,
@@ -1861,10 +1861,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 20,
"ambiguous_runtime": 21,
"参数/模板问题": 1
},
"failureCount": 21,
"failureCount": 22,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1874,8 +1874,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 21,
"unresolvedFailureCount": 21
"total": 22,
"unresolvedFailureCount": 22
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2289,7 +2289,7 @@
"decisionSuccessRate": 0.2883,
"decisionTotal": 163,
"failureBreakdown": {
"ambiguous_runtime": 93,
"ambiguous_runtime": 94,
"backend_operator": 2,
"framework_architecture_unsupported": 83,
"memory_capacity": 5,
@@ -2298,15 +2298,15 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 938,
"failureCount": 939,
"failureRate": 0.9523,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 47,
"successRate": 0.0477,
"total": 985,
"unresolvedFailureCount": 822
"total": 986,
"unresolvedFailureCount": 823
},
"vllm": {
"attributableFailureCount": 227,
@@ -2400,22 +2400,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 21,
"ambiguous_runtime": 22,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 27,
"参数/模板问题": 7
},
"failureCount": 61,
"failureCount": 62,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 61,
"unresolvedFailureCount": 28
"total": 62,
"unresolvedFailureCount": 29
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2436,7 +2436,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T01:16:26.312138+00:00",
"generatedAt": "2026-09-10T01:42:35.047837+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2538,22 +2538,22 @@
"decisionSuccessRate": 0.1053,
"decisionTotal": 19,
"failureBreakdown": {
"ambiguous_runtime": 23,
"ambiguous_runtime": 24,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 17,
"验证失败": 22
},
"failureCount": 79,
"failureRate": 0.9753,
"failureCount": 80,
"failureRate": 0.9756,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0247,
"total": 81,
"unresolvedFailureCount": 62
"successRate": 0.0244,
"total": 82,
"unresolvedFailureCount": 63
},
"Iluvatar_bi-100": {
"attributableFailureCount": 0,
@@ -2627,20 +2627,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 51,
"ambiguous_runtime": 52,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 76,
"failureCount": 77,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 76,
"unresolvedFailureCount": 75
"total": 77,
"unresolvedFailureCount": 76
},
"MetaX_c-500": {
"attributableFailureCount": 38,
@@ -3245,9 +3245,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
@@ -3259,8 +3259,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0,
@@ -4071,24 +4071,24 @@
"decisionSuccessRate": 0.3333,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 3,
"tokenizer_compatibility": 1
},
"failureCount": 10,
"failureRate": 0.8333,
"failureCount": 11,
"failureRate": 0.8462,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T23:14:19.142084+00:00",
"lastTerminalAt": "2026-09-10T01:42:34.770281+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.1667,
"successRate": 0.1538,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 12,
"unresolvedFailureCount": 6
"total": 13,
"unresolvedFailureCount": 7
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 4,
@@ -5804,6 +5804,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|28": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 28,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -6741,15 +6765,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1474,
"totalRecords": 1558,
"terminalRecords": 1476,
"totalRecords": 1560,
"totals": {
"attributableFailureCount": 390,
"decisionFailureRate": 0.8904,
"decisionSuccessRate": 0.1096,
"decisionTotal": 438,
"failureBreakdown": {
"ambiguous_runtime": 267,
"ambiguous_runtime": 269,
"backend_operator": 25,
"framework_architecture_unsupported": 266,
"memory_capacity": 11,
@@ -6761,21 +6785,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1426,
"failureRate": 0.9674,
"failureCount": 1428,
"failureRate": 0.9675,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 48,
"successRate": 0.0326,
"total": 1474,
"unresolvedFailureCount": 1034
"successRate": 0.0325,
"total": 1476,
"unresolvedFailureCount": 1036
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 Iluvatar_mrv-100 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 Iluvatar_bi-150 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 Vastai_va16 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。",
@@ -6783,7 +6807,7 @@
"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 Mthreads_s4000 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 Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"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 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。",
@@ -6804,6 +6828,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1558,
"summarizedRecords": 1560,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T01:42:34.770281+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:37:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481718", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T01:16:26.008857+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505087", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T01:16:26.008867+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505110", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T01:16:26.008832+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:11:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505076", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T05:05:30.903823+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T04:57:23+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4461505", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_text"], "framework": "", "lastSyncTime": "2026-09-07T04:51:27.989190+00:00", "modelId": "ValueFX/Qwen3.8-27B-CCCP-S", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T04:49:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4218096", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["RWKV7ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-07T04:34:12.697096+00:00", "modelId": "fla-hub/rwkv7-7.2B-g0", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T04:19:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079209", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-07T03:57:59.407849+00:00", "modelId": "nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T03:49:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609084", "taskType": "text-generation", "verifyResult": -1}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "300c325ad821830e402550bd8cda0f7d62d71b78f20aace9a7bb2f0cae651782",
".modelhub_state/architecture_history_backfill.json": "dd2816ae2cc2edc10e9685d4e94fbb1eb281377a7791a0de9e283f49a82e4c3b",
".modelhub_state/market_intelligence.json": "af49dbb21a8fbdfd8e92993c69a74aff7b7bb73f844adf62d6acb943a32067ac",
".modelhub_state/official_capabilities.json": "d8bd8167e13ecd0be5e08fc09939e0201e5dfdd0c3d4a6ea3b2414ebb0dc8a7c",
".modelhub_state/outcome_checkpoint.json": "f936a227a61390a0c040a6651d9ac5030e35df9041c1f32c6df3d6e7e31a6741",
".modelhub_state/architecture_compatibility_blacklist.json": "222376805128e40cc69477b699ed977028be29e5b32b8cccfa7356102261b0b4",
".modelhub_state/architecture_history_backfill.json": "b32b25b1c3b4f3f07ee18fcc8326b20b06e0518fbef46efde0389afa3b2c941b",
".modelhub_state/market_intelligence.json": "3ea294e1963b0eda3612de0c8f6a7db442c79ab276c91e5d38ff224600f05745",
".modelhub_state/official_capabilities.json": "4a80c948050a80bc6feae443b72edeb4a0a363e2b672d7a65ec60a6f508c32b8",
".modelhub_state/outcome_checkpoint.json": "b21e8cb14d73a238696dbf0de6323b8ecee36e7073100949f5938511d383c316",
".modelhub_state/queue_cleanup_latest.json": "9a11c448074d1c105fe90e48fb81cfc27bce5e7e08d76397232f05c4c9432a32",
".modelhub_state/recent_outcomes.jsonl": "2909d1ae1487ad6a9a486a6aa681d5d6388cc7b52391d21661107fcbb0feedeb",
".modelhub_state/recovery_active_tasks.jsonl": "46b5f108e70d029c4ffe26ae37c1ab2a37e877b2cd156582872b70cb6be15cb2",
".modelhub_state/recovery_intents.jsonl": "c797963875be6e94b561ee51815bfc091cb3a3c3a65c89b2c55e5f9c6d4cc6b4",
".modelhub_state/recent_outcomes.jsonl": "5ee96d7694d22e5bc45d6f10cafb3f8f8e4552099fa584e5e4d7b847b78b6a5b",
".modelhub_state/recovery_active_tasks.jsonl": "01f2bf359b7efe90df914706e286cce4fe542de0096f87620b2bea504ada28cd",
".modelhub_state/recovery_intents.jsonl": "d129be3b1bc971b1a00e11f9a1d90d25791997efa32571804ec898ffd1a9f1ac",
".modelhub_state/routing_intelligence.json": "9728fc332171710c9563b5aee57d999c7c39f45a5a695c768154b5b8537aa569",
".modelhub_state/submission_exclusions.jsonl": "363b21d9f5526f9b072e4f5ff55cc1ff126e844da64fb08a7b6e4d09b2559cdb",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "9e965a67faea9c161b6eace8692b9867848771b0d6b3404b41e880245a7a48d1",
"outcomes/submissions.jsonl": "3f353d337dd78019babdc36d9c6cc764c82ce9024073367355d8a167cda9b032"
"outcomes/submissions.jsonl": "cc601735c50eba062874b6e0376a601d4f41be2607e679ffcedc57d869b0ce7d"
},
"generation": 4887,
"generation": 4888,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T01:41:34.127343+00:00",
"updatedAt": "2026-09-10T01:44:14.098643+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}

View File

@@ -217,7 +217,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:14:15.399910+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:05:58.785747+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669358", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:14:15.399880+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385168, "estimatedRequiredGiB": 13.339, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11935116462, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11935116462}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:07:54.384483+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669411", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:35:22.599877+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195521, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018195521}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:28:09.689378+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669860", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:35:22.599809+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443106}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:28:09.692486+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669865", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:35:22.599825+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5705684944, "estimatedRequiredGiB": 6.387, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5714910031, "modelscopeLicense": null, "modelscopeParams": 8031506432, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5714910031}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:28:09.693682+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669866", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T00:59:44.608188+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14399972864, "estimatedRequiredGiB": 16.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 14402000339, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7199932416, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14402000339}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T16:48:59.678173+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4672290", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T02:37:59.437424+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3055418240, "estimatedRequiredGiB": 3.417, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 3057371034, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1527668736, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3057371034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T18:34:36.628828+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4674757", "taskType": "text-generation", "verifyResult": null}
@@ -508,7 +507,7 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T23:05:47.802235+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778320, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T15:04:57.783545+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4742256", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T00:59:29.336134+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T16:58:40.742484+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4743575", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T01:25:11.702629+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T17:17:51.553387+00:00", "targetGpu": "Vastai_va16", "taskId": "4743762", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-09T17:36:33.499638+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4743919", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T01:42:34.770227+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T17:36:33.499638+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4743919", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-09T17:53:28.482893+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4744096", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-09T18:11:56.418165+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4744370", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-09T18:31:44.217327+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4744546", "taskType": "text-generation", "verifyResult": null}