state: generation 5272 (cycle)

This commit is contained in:
2026-09-10 16:56:17 +00:00
parent a339232da1
commit 80d1dde7f5
9 changed files with 1957 additions and 1957 deletions

View File

@@ -1311,7 +1311,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-10T16:53:16.474648+00:00", "generatedAt": "2026-09-10T16:56:16.559929+00:00",
"summary": { "summary": {
"activeBlockCount": 66, "activeBlockCount": 66,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": { "11": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 374, "listingErrors": 375,
"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": 11, "nextAccountIndex": 0,
"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": "2026-09-10T16:53:16.450401+00:00", "updatedAt": "2026-09-10T16:56:16.536654+00:00",
"version": 1 "version": 1
} }

View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-09-10T16:37:44.581340+00:00", "communityAttemptedAt": "2026-09-10T16:54:24.256447+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-09-10T16:37:44.581340+00:00", "communityUpdatedAt": "2026-09-10T16:54:24.256447+00:00",
"frameworkAttemptedAt": "2026-09-10T15:27:32.924657+00:00", "frameworkAttemptedAt": "2026-09-10T15:27:32.924657+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
@@ -416,7 +416,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T16:51:32.178688+00:00", "generatedAt": "2026-09-10T16:54:24.256447+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": "2026-09-10T16:44:51.166987+00:00", "generatedAt": "2026-09-10T16:54:17.522980+00:00",
"lastSyncTime": "2026-09-10T16:44:50.902809+00:00", "lastSyncTime": "2026-09-10T16:54:17.206935+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1545,24 +1545,24 @@
"decisionSuccessRate": 0.0909, "decisionSuccessRate": 0.0909,
"decisionTotal": 22, "decisionTotal": 22,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 23, "ambiguous_runtime": 24,
"framework_architecture_unsupported": 18, "framework_architecture_unsupported": 18,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"验证失败": 39 "验证失败": 39
}, },
"failureCount": 82, "failureCount": 83,
"failureRate": 0.9762, "failureRate": 0.9765,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 2,
"successRate": 0.0238, "successRate": 0.0235,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 84, "total": 85,
"unresolvedFailureCount": 62 "unresolvedFailureCount": 63
}, },
"Cambricon_mlu-370-x8|unknown|text-generation": { "Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 7, "attributableFailureCount": 7,
@@ -2000,7 +2000,7 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 32, "decisionTotal": 32,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 27, "ambiguous_runtime": 28,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 22, "framework_architecture_unsupported": 22,
"memory_capacity": 1, "memory_capacity": 1,
@@ -2009,7 +2009,7 @@
"runtime_memory": 2, "runtime_memory": 2,
"参数/模板问题": 3 "参数/模板问题": 3
}, },
"failureCount": 62, "failureCount": 63,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -2019,8 +2019,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Mthreads_s4000", "targetGpu": "Mthreads_s4000",
"taskType": "text-generation", "taskType": "text-generation",
"total": 62, "total": 63,
"unresolvedFailureCount": 30 "unresolvedFailureCount": 31
}, },
"Sunrise_pt-200-x1|unknown|text-generation": { "Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -2296,7 +2296,7 @@
"decisionSuccessRate": 0.2759, "decisionSuccessRate": 0.2759,
"decisionTotal": 174, "decisionTotal": 174,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 117, "ambiguous_runtime": 118,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 88, "framework_architecture_unsupported": 88,
"memory_capacity": 5, "memory_capacity": 5,
@@ -2305,15 +2305,15 @@
"参数/模板问题": 56, "参数/模板问题": 56,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 972, "failureCount": 973,
"failureRate": 0.9529, "failureRate": 0.953,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 48, "successCount": 48,
"successRate": 0.0471, "successRate": 0.047,
"total": 1020, "total": 1021,
"unresolvedFailureCount": 846 "unresolvedFailureCount": 847
}, },
"vllm": { "vllm": {
"attributableFailureCount": 240, "attributableFailureCount": 240,
@@ -2321,7 +2321,7 @@
"decisionSuccessRate": 0.0083, "decisionSuccessRate": 0.0083,
"decisionTotal": 242, "decisionTotal": 242,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 177, "ambiguous_runtime": 178,
"backend_operator": 33, "backend_operator": 33,
"framework_architecture_unsupported": 169, "framework_architecture_unsupported": 169,
"memory_capacity": 6, "memory_capacity": 6,
@@ -2332,15 +2332,15 @@
"tokenizer_compatibility": 3, "tokenizer_compatibility": 3,
"参数/模板问题": 24 "参数/模板问题": 24
}, },
"failureCount": 442, "failureCount": 443,
"failureRate": 0.9955, "failureRate": 0.9955,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 2, "successCount": 2,
"successRate": 0.0045, "successRate": 0.0045,
"total": 444, "total": 445,
"unresolvedFailureCount": 201 "unresolvedFailureCount": 202
}, },
"vllm-mlu": { "vllm-mlu": {
"attributableFailureCount": 7, "attributableFailureCount": 7,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-10T16:44:51.162108+00:00", "generatedAt": "2026-09-10T16:54:17.517562+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2523,21 +2523,21 @@
"decisionSuccessRate": 0.0909, "decisionSuccessRate": 0.0909,
"decisionTotal": 22, "decisionTotal": 22,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 23, "ambiguous_runtime": 24,
"framework_architecture_unsupported": 18, "framework_architecture_unsupported": 18,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"验证失败": 39 "验证失败": 39
}, },
"failureCount": 82, "failureCount": 83,
"failureRate": 0.9762, "failureRate": 0.9765,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 2,
"successRate": 0.0238, "successRate": 0.0235,
"total": 84, "total": 85,
"unresolvedFailureCount": 62 "unresolvedFailureCount": 63
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"attributableFailureCount": 17, "attributableFailureCount": 17,
@@ -2679,7 +2679,7 @@
"decisionSuccessRate": 0.0571, "decisionSuccessRate": 0.0571,
"decisionTotal": 35, "decisionTotal": 35,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 27, "ambiguous_runtime": 28,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 22, "framework_architecture_unsupported": 22,
"memory_capacity": 1, "memory_capacity": 1,
@@ -2689,15 +2689,15 @@
"参数/模板问题": 10, "参数/模板问题": 10,
"验证失败": 26 "验证失败": 26
}, },
"failureCount": 96, "failureCount": 97,
"failureRate": 0.9796, "failureRate": 0.9798,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 2,
"successRate": 0.0204, "successRate": 0.0202,
"total": 98, "total": 99,
"unresolvedFailureCount": 63 "unresolvedFailureCount": 64
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"attributableFailureCount": 36, "attributableFailureCount": 36,
@@ -4116,15 +4116,15 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 2,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 10, "ambiguous_runtime": 11,
"framework_architecture_unsupported": 1, "framework_architecture_unsupported": 1,
"tokenizer_compatibility": 1 "tokenizer_compatibility": 1
}, },
"failureCount": 12, "failureCount": 13,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T13:30:05.632388+00:00", "lastTerminalAt": "2026-09-10T16:54:17.206907+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -4132,8 +4132,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 12, "total": 13,
"unresolvedFailureCount": 10 "unresolvedFailureCount": 11
}, },
"Cambricon_mlu-370-x8|unknown|text-generation": { "Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -4426,16 +4426,16 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 5, "decisionTotal": 5,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 7, "ambiguous_runtime": 8,
"backend_operator": 3, "backend_operator": 3,
"framework_architecture_unsupported": 1, "framework_architecture_unsupported": 1,
"runtime_memory": 1 "runtime_memory": 1
}, },
"failureCount": 12, "failureCount": 13,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T10:57:49.001753+00:00", "lastTerminalAt": "2026-09-10T16:54:17.206935+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -4443,8 +4443,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Mthreads_s4000", "targetGpu": "Mthreads_s4000",
"taskType": "text-generation", "taskType": "text-generation",
"total": 12, "total": 13,
"unresolvedFailureCount": 7 "unresolvedFailureCount": 8
}, },
"Sunrise_pt-200-x1|unknown|text-generation": { "Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -7193,15 +7193,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1608, "terminalRecords": 1610,
"totalRecords": 1695, "totalRecords": 1697,
"totals": { "totals": {
"attributableFailureCount": 421, "attributableFailureCount": 421,
"decisionFailureRate": 0.8901, "decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099, "decisionSuccessRate": 0.1099,
"decisionTotal": 473, "decisionTotal": 473,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 361, "ambiguous_runtime": 363,
"backend_operator": 40, "backend_operator": 40,
"framework_architecture_unsupported": 272, "framework_architecture_unsupported": 272,
"memory_capacity": 11, "memory_capacity": 11,
@@ -7213,30 +7213,31 @@
"参数/模板问题": 98, "参数/模板问题": 98,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1556, "failureCount": 1558,
"failureRate": 0.9677, "failureRate": 0.9677,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 3, "platformFailureCount": 3,
"successCount": 52, "successCount": 52,
"successRate": 0.0323, "successRate": 0.0323,
"total": 1608, "total": 1610,
"unresolvedFailureCount": 1132 "unresolvedFailureCount": 1134
}, },
"warnings": [ "warnings": [
"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 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 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 Ascend_910-b4 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 Sunrise_pt-200-x1 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。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 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 hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU 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 Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"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-x4|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Mthreads_s4000|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7251,11 +7252,10 @@
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。" "组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1695, "summarizedRecords": 1697,
"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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T16:54:17.206907+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:49:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497075", "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": "2026-09-10T16:54:17.206935+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:45:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532021", "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": "2026-09-10T16:37:38.117587+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:33:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505124", "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": "2026-09-10T16:37:38.117587+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:33:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505124", "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": "2026-09-10T16:37:38.117560+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:31:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505123", "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": "2026-09-10T16:37:38.117560+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:31:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505123", "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": "2026-09-10T16:05:31.804335+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T15:59:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457978", "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": "2026-09-10T16:05:31.804335+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T15:59:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457978", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-08T06:21:18.620967+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-08T06:11:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4525689", "taskType": "text-generation", "verifyResult": 1} {"failReason": null, "framework": "", "lastSyncTime": "2026-09-08T06:21:18.620967+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-08T06:11:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4525689", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T06:03:35.611314+00:00", "modelId": "nightmedia/Qwen3-4B-Element8-Eva-Heretic-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:03:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079395", "taskType": "text-generation", "verifyResult": -1} {"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T06:03:35.611314+00:00", "modelId": "nightmedia/Qwen3-4B-Element8-Eva-Heretic-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:03:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079395", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T05:49:30.800091+00:00", "modelId": "nv-community/Qwen3-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T05:43:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079985", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T05:49:30.800091+00:00", "modelId": "nv-community/Qwen3-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T05:43:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079985", "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": "2026-09-08T05:49:30.800105+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Qwen-32B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T05:43:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079986", "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": ["AquilaDenseForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-08T05:49:30.800060+00:00", "modelId": "BAAI/AquilaDense-7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T05:39:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079957", "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", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "037fd20179183cab6cdeb7032fa3b0ea3626667d57555f9757ee9eb035e9a7de", ".modelhub_state/architecture_compatibility_blacklist.json": "532524826ecd544044fb670a533c02fe052640aea9ff6eafe32f9499096b6533",
".modelhub_state/architecture_history_backfill.json": "2317dbf3d0fe85fc42518ddef4fcf23b0236154bd706fd0ffcb8eac433297f76", ".modelhub_state/architecture_history_backfill.json": "511215c5209ab85df91c26b5e8f6f9bf9362bc0fd5f5ddb992479635c61e11e5",
".modelhub_state/market_intelligence.json": "ad2373b702c4264bb2fcf301df6a2c3311093c69b343f78db2a220acc2b457a2", ".modelhub_state/market_intelligence.json": "2175b50fb289252ce4e69e5e1d151db496d6f9ed52711ef36334e16acab29d50",
".modelhub_state/official_capabilities.json": "98cad5983074b8baea642272821372321e82ca562bd4bc915e0c45dfd2440418", ".modelhub_state/official_capabilities.json": "0270210e6bd28c32616474ebc472dd4dc4cac64dee7a5df8b4bca114e27538c4",
".modelhub_state/outcome_checkpoint.json": "b49bbe0388a8215fec8cbc541e2cc4981f08225298de871e859f94f36c3fb9fb", ".modelhub_state/outcome_checkpoint.json": "f8915f4d8eefb5368690eef515748467d4fc4660d5c8f851e1dd84747bd9817c",
".modelhub_state/queue_cleanup_latest.json": "c4c0c2f745124fbabf68b2aa082c5aeee0f45dbb41d40369e8064e674a33adbe", ".modelhub_state/queue_cleanup_latest.json": "c4c0c2f745124fbabf68b2aa082c5aeee0f45dbb41d40369e8064e674a33adbe",
".modelhub_state/recent_outcomes.jsonl": "2a9da9c02f313330147536b286aea8170eacf11940a458b71a935952ab7452ac", ".modelhub_state/recent_outcomes.jsonl": "83bde283f815736ab38036c5b31fbb67a03aee802e47a1babd2bbf9ca58a261f",
".modelhub_state/recovery_active_tasks.jsonl": "80824d78768c45465c33a628634932962ebd08dbcdb021bd86b20fab3a1e97bd", ".modelhub_state/recovery_active_tasks.jsonl": "7c89929110d728449e26e82d186f01564da4b59ae6d2a1814d643e583ab365a6",
".modelhub_state/recovery_intents.jsonl": "77c664af35cc84e7fa4b5048b13b4d174c74e739280c7053d78951259fd89362", ".modelhub_state/recovery_intents.jsonl": "cf12e30a38ffd029aa993ad4300c6f1a1320c0dc8a1955523f39806012d9b03e",
".modelhub_state/routing_intelligence.json": "bcaf2013af1725c91c403ee60ebea6ce240abe9c172497b6086649b19fe2a2a9", ".modelhub_state/routing_intelligence.json": "bcaf2013af1725c91c403ee60ebea6ce240abe9c172497b6086649b19fe2a2a9",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03", ".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba", ".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "b825b21af42e5406538478522c80028c136d59b0b4682500784c593298293d8b", "ledger/submissions.jsonl": "b825b21af42e5406538478522c80028c136d59b0b4682500784c593298293d8b",
"outcomes/submissions.jsonl": "a586cdf2049d2a9903a1e7b423d740a29c6547aac344621237f61dc993f79af7" "outcomes/submissions.jsonl": "a586cdf2049d2a9903a1e7b423d740a29c6547aac344621237f61dc993f79af7"
}, },
"generation": 5271, "generation": 5272,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-10T16:53:16.554737+00:00", "updatedAt": "2026-09-10T16:56:17.243781+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42" "writerId": "18252d8a8ef94333abd55823b2d81c42"
} }