state: generation 4955 (cycle)

This commit is contained in:
2026-09-10 04:47:26 +00:00
parent 37026ce883
commit 17208b0206
11 changed files with 2077 additions and 2032 deletions

View File

@@ -1325,7 +1325,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T04:44:48.543422+00:00",
"generatedAt": "2026-09-10T04:47:25.092657+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -11,7 +11,7 @@
"1": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 353,
"listingErrors": 354,
"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": 1,
"nextAccountIndex": 2,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T04:44:48.520705+00:00",
"updatedAt": "2026-09-10T04:47:25.068249+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T04:43:25.935913+00:00",
"generatedAt": "2026-09-10T04:45:56.990796+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": "2026-09-10T04:27:59.073636+00:00",
"lastSyncTime": "2026-09-10T04:27:58.701482+00:00",
"generatedAt": "2026-09-10T04:45:49.713641+00:00",
"lastSyncTime": "2026-09-10T04:45:49.293213+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1762,22 +1762,22 @@
"decisionSuccessRate": 0.2,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"backend_operator": 3,
"framework_architecture_unsupported": 1
},
"failureCount": 6,
"failureRate": 0.8571,
"failureCount": 7,
"failureRate": 0.875,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.1429,
"successRate": 0.125,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 2
"total": 8,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 14,
@@ -2243,14 +2243,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 9,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1
},
"failureCount": 43,
"failureCount": 44,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2260,8 +2260,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 43,
"unresolvedFailureCount": 8
"total": 44,
"unresolvedFailureCount": 9
}
},
"frameworkSummaries": {
@@ -2333,7 +2333,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 230,
"failureBreakdown": {
"ambiguous_runtime": 134,
"ambiguous_runtime": 135,
"backend_operator": 24,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2344,15 +2344,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 386,
"failureCount": 387,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 386,
"unresolvedFailureCount": 155
"total": 387,
"unresolvedFailureCount": 156
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2399,19 +2399,19 @@
"decisionSuccessRate": 0.2,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"backend_operator": 3,
"framework_architecture_unsupported": 1
},
"failureCount": 6,
"failureRate": 0.8571,
"failureCount": 7,
"failureRate": 0.875,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.1429,
"total": 7,
"unresolvedFailureCount": 2
"successRate": 0.125,
"total": 8,
"unresolvedFailureCount": 3
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 32,
@@ -2455,7 +2455,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T04:27:59.069416+00:00",
"generatedAt": "2026-09-10T04:45:49.709300+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2599,7 +2599,7 @@
"decisionSuccessRate": 0.24,
"decisionTotal": 25,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"backend_operator": 5,
"framework_architecture_unsupported": 8,
"model_load": 4,
@@ -2607,15 +2607,15 @@
"参数/模板问题": 1,
"验证失败": 30
},
"failureCount": 60,
"failureRate": 0.9091,
"failureCount": 61,
"failureRate": 0.9104,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.0909,
"total": 66,
"unresolvedFailureCount": 41
"successRate": 0.0896,
"total": 67,
"unresolvedFailureCount": 42
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 68,
@@ -2762,7 +2762,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"model_load": 3,
@@ -2771,15 +2771,15 @@
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 83,
"failureCount": 84,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 83,
"unresolvedFailureCount": 45
"total": 84,
"unresolvedFailureCount": 46
}
},
"observedGpuMemoryGiB": {
@@ -3212,6 +3212,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|aquila3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -4083,19 +4106,19 @@
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 4,
"attributableFailureCount": 3,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 6,
"decisionFailureRate": 0.6,
"decisionSuccessRate": 0.4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 2,
"tokenizer_compatibility": 1
},
"failureCount": 14,
"failureRate": 0.875,
"failureCount": 13,
"failureRate": 0.8667,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T01:59:31.241099+00:00",
@@ -4103,10 +4126,10 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.125,
"successRate": 0.1333,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 16,
"total": 15,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
@@ -4655,16 +4678,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 8,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 16,
"failureCount": 17,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T02:50:12.317776+00:00",
"lastTerminalAt": "2026-09-10T04:45:49.293187+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4672,8 +4695,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 6
"total": 17,
"unresolvedFailureCount": 7
}
},
"recentProfileCombinationStats": {
@@ -5801,6 +5824,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|aquila3|none|12": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -6858,15 +6905,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1500,
"totalRecords": 1587,
"terminalRecords": 1502,
"totalRecords": 1589,
"totals": {
"attributableFailureCount": 399,
"decisionFailureRate": 0.8906,
"decisionSuccessRate": 0.1094,
"decisionTotal": 448,
"failureBreakdown": {
"ambiguous_runtime": 282,
"ambiguous_runtime": 284,
"backend_operator": 29,
"framework_architecture_unsupported": 270,
"memory_capacity": 11,
@@ -6878,21 +6925,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1451,
"failureRate": 0.9673,
"failureCount": 1453,
"failureRate": 0.9674,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0327,
"total": 1500,
"unresolvedFailureCount": 1050
"successRate": 0.0326,
"total": 1502,
"unresolvedFailureCount": 1052
},
"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 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。",
"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。",
@@ -6900,7 +6947,7 @@
"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 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。",
"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。",
@@ -6921,6 +6968,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1587,
"summarizedRecords": 1589,
"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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T04:45:49.293187+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:43:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493603", "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": "2026-09-10T04:27:58.701433+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:25:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471917", "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": "2026-09-10T04:27:58.701482+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:23:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471910", "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": "2026-09-10T04:27:58.701457+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:21:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471915", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T10:17:44.109335+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T09:57:22+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4458964", "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": ["GPTNeoForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-07T09:53:28.210465+00:00", "modelId": "KoboldAI/GPT-Neo-2.7B-Janeway", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T09:45:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079146", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T09:29:22.999691+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T09:17:22+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4471037", "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", "failureUnsupportedArchitectures": ["NemotronHForCausalLM"], "framework": "", "lastSyncTime": "2026-09-07T09:00:01.243299+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T08:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4471038", "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

@@ -89,7 +89,6 @@
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T23:29:59.918683+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636372", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T23:30:00.029529+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636376", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T23:30:00.025922+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636375", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "submitTime": "2026-09-05T00:45:53.655886+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4637779", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "modelId": "sapientinc/HRM-Text-1B", "submitTime": "2026-09-05T02:00:39.906273+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4638916", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-05T02:00:39.877205+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4638914", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-05T02:00:39.878542+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4638915", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "782ef98edf37e25d68a15242d12fe188678fcc74153267f61644f8bf9926014e",
".modelhub_state/architecture_history_backfill.json": "08a78a1a493ce07e397f70b98882d0957925e257db1d0dc575d87f0f59f3b20f",
".modelhub_state/market_intelligence.json": "e10387252460632ccd3cb066ed3be63e881027454fba54d642ca3b75f77fa2fc",
".modelhub_state/official_capabilities.json": "1d155cda85cab61d4f061b8dc6530de4a1073a6b7619bf814b4bf9f438629246",
".modelhub_state/outcome_checkpoint.json": "8bae6846cd09fbddff71e02af8f0a5278d435ed404588c853af3c990780f5f60",
".modelhub_state/architecture_compatibility_blacklist.json": "0e75900b88753b99e4e08818f8c9989c8e02fc3c39368d0832b8fd9fd6ba09e6",
".modelhub_state/architecture_history_backfill.json": "773f92dc3ecd81415c36a8ae5e160281be931860513c583077842e848678363d",
".modelhub_state/market_intelligence.json": "b68ba15f27db566e5d9e69cb3b476a49c63822a4d063ff9f11ddc2e3265b23d7",
".modelhub_state/official_capabilities.json": "28bed4369f8eeb85a4695300583681d7d6fc245c1803af013061d86f74a519e4",
".modelhub_state/outcome_checkpoint.json": "f123ec16e7df7df588b42b9d139d2ab47d25afbdaaac32795a1042355bdb7837",
".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99",
".modelhub_state/recent_outcomes.jsonl": "c9090ab305007a3773601d94b15a1bd75a8d8dc0e31cca1aa7e46be5c8c780b6",
".modelhub_state/recovery_active_tasks.jsonl": "c4a48e68533d1f59f77e23f857a8817136dad3712fafdea357b5b62b85e2df0f",
".modelhub_state/recovery_intents.jsonl": "ee6c97effe765f35c396f1e7f975c4a180ee5485ce4fd8e2482ea018074aa1c6",
".modelhub_state/recent_outcomes.jsonl": "e28db23599a9d908223612e0fa980594148a77f1acc6cccec525e210fa3ca35d",
".modelhub_state/recovery_active_tasks.jsonl": "858321c896f1cba09731da900d735027493de2dfa59510ac129d5e2cf2998ee8",
".modelhub_state/recovery_intents.jsonl": "0de1c1f7357a7c01879d8d0c953f1b01f8b0fdd2c3da449e2705b050069518f6",
".modelhub_state/routing_intelligence.json": "2c10dfed0a26c6bc51f09f69009667713989adad52ee2398495736003f8b05c0",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "62d96a5e698320873d12db5f664a4a0e841ea10716299772bd4029396ab01914",
"outcomes/submissions.jsonl": "ffb7b8c8faabe057c48e9d220a3d453695bedea146f96deba7b83d00b89a737f"
"ledger/submissions.jsonl": "4d2bbfc439a137759b4698122a8725280b082c541629542d0329d6b9040fe6dc",
"outcomes/submissions.jsonl": "e7ef9f0450e529c73e89c5cd1d774421d0e33158d26ca828bacfdf64c7f20d42"
},
"generation": 4954,
"generation": 4955,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T04:44:48.624628+00:00",
"updatedAt": "2026-09-10T04:47:25.999698+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}

View File

@@ -97,7 +97,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T10:41:43.740753+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5700679600, "estimatedRequiredGiB": 6.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5709884743, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5709884743}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T02:38:10.748196+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4639409", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:40:37.707812+00:00", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8dbcfce641caa83ec7080451f0410ae2c4732d92c35c6ea116cea836d3424ea2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2076674432, "estimatedRequiredGiB": 11.564, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10347343046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1942653248, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "custom_tag:edge", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10347343046}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:38:07.789820+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641229", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:57:50.112723+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "7fcefcc66e6b781d939ce31d9aa1c7a89bdfb773b9556e6dcde4e21754b1189f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4610579744, "estimatedRequiredGiB": 25.463, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 22784105135, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4326350848, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22784105135}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:56:19.745119+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641463", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T12:57:50.112639+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612468, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "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": 17788612468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:56:26.818323+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641464", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397755+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:01.097550+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641563", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397684+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:09.008584+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641565", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397729+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:09.000926+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641564", "taskType": "text-generation", "verifyResult": null}