state: generation 5102 (cycle)

This commit is contained in:
2026-09-10 09:49:20 +00:00
parent d5ad209faa
commit 184766a83e
9 changed files with 2219 additions and 2221 deletions

View File

@@ -1317,7 +1317,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-10T09:46:32.562016+00:00", "generatedAt": "2026-09-10T09:49:18.743475+00:00",
"summary": { "summary": {
"activeBlockCount": 66, "activeBlockCount": 66,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -51,7 +51,7 @@
"4": { "4": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 362, "listingErrors": 363,
"nextPage": 1, "nextPage": 1,
"recordsScanned": 0, "recordsScanned": 0,
"uniqueRecords": 0 "uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00", "cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0, "failureLogsInspected": 0,
"mode": "incremental_decision_only", "mode": "incremental_decision_only",
"nextAccountIndex": 4, "nextAccountIndex": 5,
"recordsScanned": 0, "recordsScanned": 0,
"seenTaskIds": [], "seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00", "startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0, "terminalRecords": 0,
"uniqueRecords": 0, "uniqueRecords": 0,
"updatedAt": "2026-09-10T09:46:32.534885+00:00", "updatedAt": "2026-09-10T09:49:18.694062+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,7 +416,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T09:44:59.525864+00:00", "generatedAt": "2026-09-10T09:47:42.975669+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-10T09:38:19.296061+00:00", "generatedAt": "2026-09-10T09:47:33.599443+00:00",
"lastSyncTime": "2026-09-10T09:38:19.106782+00:00", "lastSyncTime": "2026-09-10T09:47:33.262404+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2147,12 +2147,12 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 44, "decisionTotal": 44,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 50, "ambiguous_runtime": 51,
"framework_architecture_unsupported": 38, "framework_architecture_unsupported": 38,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 5 "model_load": 5
}, },
"failureCount": 94, "failureCount": 95,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -2162,8 +2162,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Vastai_va16", "targetGpu": "Vastai_va16",
"taskType": "text-generation", "taskType": "text-generation",
"total": 94, "total": 95,
"unresolvedFailureCount": 50 "unresolvedFailureCount": 51
}, },
"hygon_k100-ai|llamacpp|text-generation": { "hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -2235,14 +2235,14 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 35, "decisionTotal": 35,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 13, "ambiguous_runtime": 14,
"framework_architecture_unsupported": 27, "framework_architecture_unsupported": 27,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 3, "model_load": 3,
"repository_structure": 3, "repository_structure": 3,
"runtime_memory": 1 "runtime_memory": 1
}, },
"failureCount": 48, "failureCount": 49,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -2252,8 +2252,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 48, "total": 49,
"unresolvedFailureCount": 13 "unresolvedFailureCount": 14
} }
}, },
"frameworkSummaries": { "frameworkSummaries": {
@@ -2325,7 +2325,7 @@
"decisionSuccessRate": 0.0042, "decisionSuccessRate": 0.0042,
"decisionTotal": 236, "decisionTotal": 236,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 155, "ambiguous_runtime": 157,
"backend_operator": 29, "backend_operator": 29,
"framework_architecture_unsupported": 169, "framework_architecture_unsupported": 169,
"memory_capacity": 6, "memory_capacity": 6,
@@ -2336,15 +2336,15 @@
"tokenizer_compatibility": 3, "tokenizer_compatibility": 3,
"参数/模板问题": 21 "参数/模板问题": 21
}, },
"failureCount": 412, "failureCount": 414,
"failureRate": 0.9976, "failureRate": 0.9976,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 1, "successCount": 1,
"successRate": 0.0024, "successRate": 0.0024,
"total": 413, "total": 415,
"unresolvedFailureCount": 176 "unresolvedFailureCount": 178
}, },
"vllm-mlu": { "vllm-mlu": {
"attributableFailureCount": 7, "attributableFailureCount": 7,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-10T09:38:19.291073+00:00", "generatedAt": "2026-09-10T09:47:33.595423+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2731,22 +2731,22 @@
"decisionSuccessRate": 0.2167, "decisionSuccessRate": 0.2167,
"decisionTotal": 60, "decisionTotal": 60,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 51, "ambiguous_runtime": 52,
"framework_architecture_unsupported": 40, "framework_architecture_unsupported": 40,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 6, "model_load": 6,
"参数/模板问题": 13, "参数/模板问题": 13,
"验证失败": 130 "验证失败": 130
}, },
"failureCount": 241, "failureCount": 242,
"failureRate": 0.9488, "failureRate": 0.949,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 13, "successCount": 13,
"successRate": 0.0512, "successRate": 0.051,
"total": 254, "total": 255,
"unresolvedFailureCount": 194 "unresolvedFailureCount": 195
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"attributableFailureCount": 38, "attributableFailureCount": 38,
@@ -2754,7 +2754,7 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 38, "decisionTotal": 38,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 15, "ambiguous_runtime": 16,
"framework_architecture_unsupported": 30, "framework_architecture_unsupported": 30,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 3, "model_load": 3,
@@ -2763,15 +2763,15 @@
"参数/模板问题": 8, "参数/模板问题": 8,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 88, "failureCount": 89,
"failureRate": 1.0, "failureRate": 1.0,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"total": 88, "total": 89,
"unresolvedFailureCount": 50 "unresolvedFailureCount": 51
} }
}, },
"observedGpuMemoryGiB": { "observedGpuMemoryGiB": {
@@ -4334,9 +4334,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 7 "ambiguous_runtime": 6
}, },
"failureCount": 7, "failureCount": 6,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -4348,8 +4348,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 7, "total": 6,
"unresolvedFailureCount": 7 "unresolvedFailureCount": 6
}, },
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": { "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -4563,11 +4563,9 @@
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0, "decisionSuccessRate": 1.0,
"decisionTotal": 1, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {},
"参数/模板问题": 1 "failureCount": 0,
}, "failureRate": 0.0,
"failureCount": 1,
"failureRate": 0.5,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-07T22:32:11.428244+00:00", "lastTerminalAt": "2026-09-07T22:32:11.428244+00:00",
@@ -4575,11 +4573,11 @@
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.5, "successRate": 1.0,
"targetGpu": "Vastai_va16", "targetGpu": "Vastai_va16",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 1,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 0
}, },
"Vastai_va16|vllm_fix_tokenizer|text-generation": { "Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -4607,21 +4605,21 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Vastai_va16|vllm|text-generation": { "Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 2, "attributableFailureCount": 1,
"consecutiveFailures": 2, "consecutiveFailures": 1,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 18, "ambiguous_runtime": 19,
"framework_architecture_unsupported": 2 "framework_architecture_unsupported": 1
}, },
"failureCount": 20, "failureCount": 20,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T06:56:22.046035+00:00", "lastTerminalAt": "2026-09-10T09:47:33.262382+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -4630,7 +4628,7 @@
"targetGpu": "Vastai_va16", "targetGpu": "Vastai_va16",
"taskType": "text-generation", "taskType": "text-generation",
"total": 20, "total": 20,
"unresolvedFailureCount": 18 "unresolvedFailureCount": 19
}, },
"hygon_k100-ai|llamacpp|text-generation": { "hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -4690,16 +4688,16 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 8, "decisionTotal": 8,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 10, "ambiguous_runtime": 11,
"framework_architecture_unsupported": 6, "framework_architecture_unsupported": 6,
"model_load": 1, "model_load": 1,
"repository_structure": 1 "repository_structure": 1
}, },
"failureCount": 18, "failureCount": 19,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T07:04:57.311815+00:00", "lastTerminalAt": "2026-09-10T09:47:33.262404+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -4707,8 +4705,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 18, "total": 19,
"unresolvedFailureCount": 10 "unresolvedFailureCount": 11
} }
}, },
"recentProfileCombinationStats": { "recentProfileCombinationStats": {
@@ -7058,15 +7056,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1551, "terminalRecords": 1553,
"totalRecords": 1638, "totalRecords": 1640,
"totals": { "totals": {
"attributableFailureCount": 405, "attributableFailureCount": 405,
"decisionFailureRate": 0.8882, "decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118, "decisionSuccessRate": 0.1118,
"decisionTotal": 456, "decisionTotal": 456,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 325, "ambiguous_runtime": 327,
"backend_operator": 34, "backend_operator": 34,
"framework_architecture_unsupported": 271, "framework_architecture_unsupported": 271,
"memory_capacity": 11, "memory_capacity": 11,
@@ -7078,21 +7076,21 @@
"参数/模板问题": 95, "参数/模板问题": 95,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1500, "failureCount": 1502,
"failureRate": 0.9671, "failureRate": 0.9672,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 51, "successCount": 51,
"successRate": 0.0329, "successRate": 0.0328,
"total": 1551, "total": 1553,
"unresolvedFailureCount": 1093 "unresolvedFailureCount": 1095
}, },
"warnings": [ "warnings": [
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。", "GPU Cambricon_mlu-370-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 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_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 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 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。", "GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7100,7 +7098,7 @@
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。", "GPU 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 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 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 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 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。",
@@ -7121,6 +7119,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1638, "summarizedRecords": 1640,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,5 @@
{"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": "2026-09-10T09:47:33.262404+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:47:22+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493608", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T09:47:33.262382+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:43:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477720", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-10T09:29:56.132283+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:27:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532020", "taskType": "text-generation", "verifyResult": -1} {"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-10T09:29:56.132283+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:27:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532020", "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": "2026-09-10T09:20:50.207436+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:19:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505117", "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": "2026-09-10T09:20:50.207436+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:19:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505117", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-10T09:20:50.207399+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:17:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610375", "taskType": "text-generation", "verifyResult": -1} {"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": "2026-09-10T09:20:50.207399+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:17:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610375", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"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": "2026-09-07T20:52:41.332106+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:51:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4478705", "taskType": "text-generation", "verifyResult": -1} {"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": "2026-09-07T20:52:41.332106+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:51:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4478705", "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": ["qwen3_5_mtp"], "framework": "vllm", "lastSyncTime": "2026-09-07T20:52:41.332123+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:41:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4585069", "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": ["qwen3_5_mtp"], "framework": "vllm", "lastSyncTime": "2026-09-07T20:52:41.332123+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:41:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4585069", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-07T20:39:52.300695+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:37:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458004", "taskType": "text-generation", "verifyResult": -1} {"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-07T20:39:52.300695+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:37:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458004", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-07T20:39:52.300718+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:35:22+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4461773", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-07T20:39:52.300729+00:00", "modelId": "nightmedia/Gemma3-27B-it-vl-HERETIC-GLM4.7-2200x-cp515-q6-mlx", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-07T20:31:03+00:00", "targetGpu": "Vastai_va16", "taskId": "4079310", "taskType": "text-generation", "verifyResult": null}

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", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "8bb3cbeba04080acd1871471939f916f9c33649e5ade3f171df97b69672e3260", ".modelhub_state/architecture_compatibility_blacklist.json": "1dc94434d57e3b70f3b3a420673e31a0475a8521343864f5590b6ca7a626802f",
".modelhub_state/architecture_history_backfill.json": "2492a7e3f0e0a7c29a4fa8d752d9c69ffc87f75a59d9c923c79efc8a4ef12674", ".modelhub_state/architecture_history_backfill.json": "3b1271fc8654e23725564618bcaa98cd98712cf83c35bfd6286cce43ee7115d9",
".modelhub_state/market_intelligence.json": "58b54f18d23330dc6a6b22c676548b1141c24978a4edc3ab270ed80d64610f75", ".modelhub_state/market_intelligence.json": "6a2f21cf9c4082c580df23a5a45f98de299adefc44eedd79c04f1c5a75ad6f2a",
".modelhub_state/official_capabilities.json": "2e7d2b9ffd526771dbab3dab27191e56148b82a2b2c9f6b6053ab057cf29f046", ".modelhub_state/official_capabilities.json": "c14d1e7ecf6fc74f122a5459a7a2bfdad3fa57acf1d883d690952572aa808386",
".modelhub_state/outcome_checkpoint.json": "06cba6acc20a8ab989501532da5ef5ad8acebbd67ee185a9e64217e5ad4ea501", ".modelhub_state/outcome_checkpoint.json": "a00336937dc7191e2c0d2cf88591047d307db2e2e403cad9a516b0a0c7e87db2",
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5", ".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
".modelhub_state/recent_outcomes.jsonl": "6f66aa661f4bfd87982dd4d1a850fb504ae051ec40729129e1a3e884f74078af", ".modelhub_state/recent_outcomes.jsonl": "fecfd285d8d66afeb4983b5ae2c15cc5c9bf80ecfc51b35a14589a5800c201f9",
".modelhub_state/recovery_active_tasks.jsonl": "1e0b1a57e3e9d1a66c7cca58c9c8e86308ac2fb910a610417b086bc21c81475a", ".modelhub_state/recovery_active_tasks.jsonl": "d6e24e94e3c82ee0e68549244704bf9878da817c3e8cb16f5706814d92ee5885",
".modelhub_state/recovery_intents.jsonl": "9804b510e74bdf3958b2500a48f3c737096d2ed9bcb2769587d119ae91f7689a", ".modelhub_state/recovery_intents.jsonl": "a011c7e349a3b68226a389aa1cbf9ace5f825a69e70a2aab09510bc3cf84dc38",
".modelhub_state/routing_intelligence.json": "8a52419d4402861a79d360da797632830eb2c915c1cd189832eea085096de774", ".modelhub_state/routing_intelligence.json": "8a52419d4402861a79d360da797632830eb2c915c1cd189832eea085096de774",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03", ".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76", ".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "1933ad805d1becf435394dbda5110270c499a0bd490635a19dc4240e65cfe8b1", "ledger/submissions.jsonl": "1933ad805d1becf435394dbda5110270c499a0bd490635a19dc4240e65cfe8b1",
"outcomes/submissions.jsonl": "e6be85adef265f692d087f92803b440eeef6d4048561157f9d9cda09aea505b6" "outcomes/submissions.jsonl": "e6be85adef265f692d087f92803b440eeef6d4048561157f9d9cda09aea505b6"
}, },
"generation": 5101, "generation": 5102,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-10T09:46:32.646040+00:00", "updatedAt": "2026-09-10T09:49:20.383368+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977" "writerId": "58ff5dc2a2d64b119ad1e4560700f977"
} }