state: generation 4891 (cycle)
This commit is contained in:
@@ -1306,7 +1306,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T01:49:54.176429+00:00",
|
||||
"generatedAt": "2026-09-10T01:52:54.319775+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 65,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -11,7 +11,7 @@
|
||||
"1": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 348,
|
||||
"listingErrors": 349,
|
||||
"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": "2026-09-10T01:49:54.152194+00:00",
|
||||
"updatedAt": "2026-09-10T01:52:54.296173+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-10T01:33:34.099264+00:00",
|
||||
"communityAttemptedAt": "2026-09-10T01:51:05.166551+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-10T01:33:34.099264+00:00",
|
||||
"communityUpdatedAt": "2026-09-10T01:51:05.166551+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-10T00:33:23.734278+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-10T01:48:20.990259+00:00",
|
||||
"generatedAt": "2026-09-10T01:51:05.166551+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T01:42:35.052275+00:00",
|
||||
"lastSyncTime": "2026-09-10T01:42:34.770281+00:00",
|
||||
"generatedAt": "2026-09-10T01:50:55.146422+00:00",
|
||||
"lastSyncTime": "2026-09-10T01:50:54.936024+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1565,25 +1565,25 @@
|
||||
"decisionSuccessRate": 0.2222,
|
||||
"decisionTotal": 9,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 11,
|
||||
"ambiguous_runtime": 12,
|
||||
"framework_architecture_unsupported": 5,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 5,
|
||||
"验证失败": 22
|
||||
},
|
||||
"failureCount": 45,
|
||||
"failureRate": 0.9574,
|
||||
"failureCount": 46,
|
||||
"failureRate": 0.9583,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0426,
|
||||
"successRate": 0.0417,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 47,
|
||||
"unresolvedFailureCount": 38
|
||||
"total": 48,
|
||||
"unresolvedFailureCount": 39
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -1817,11 +1817,11 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 31,
|
||||
"ambiguous_runtime": 32,
|
||||
"memory_capacity": 1,
|
||||
"验证失败": 22
|
||||
},
|
||||
"failureCount": 54,
|
||||
"failureCount": 55,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
@@ -1831,8 +1831,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 54,
|
||||
"unresolvedFailureCount": 53
|
||||
"total": 55,
|
||||
"unresolvedFailureCount": 54
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|visual-multi-modal": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -2289,7 +2289,7 @@
|
||||
"decisionSuccessRate": 0.2883,
|
||||
"decisionTotal": 163,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 94,
|
||||
"ambiguous_runtime": 96,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 83,
|
||||
"memory_capacity": 5,
|
||||
@@ -2298,15 +2298,15 @@
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 939,
|
||||
"failureRate": 0.9523,
|
||||
"failureCount": 941,
|
||||
"failureRate": 0.9524,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 47,
|
||||
"successRate": 0.0477,
|
||||
"total": 986,
|
||||
"unresolvedFailureCount": 823
|
||||
"successRate": 0.0476,
|
||||
"total": 988,
|
||||
"unresolvedFailureCount": 825
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 227,
|
||||
@@ -2436,7 +2436,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T01:42:35.047837+00:00",
|
||||
"generatedAt": "2026-09-10T01:50:55.141398+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2538,22 +2538,22 @@
|
||||
"decisionSuccessRate": 0.1053,
|
||||
"decisionTotal": 19,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 24,
|
||||
"ambiguous_runtime": 25,
|
||||
"framework_architecture_unsupported": 15,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 17,
|
||||
"验证失败": 22
|
||||
},
|
||||
"failureCount": 80,
|
||||
"failureRate": 0.9756,
|
||||
"failureCount": 81,
|
||||
"failureRate": 0.9759,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0244,
|
||||
"total": 82,
|
||||
"unresolvedFailureCount": 63
|
||||
"successRate": 0.0241,
|
||||
"total": 83,
|
||||
"unresolvedFailureCount": 64
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -2627,20 +2627,20 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 52,
|
||||
"ambiguous_runtime": 53,
|
||||
"memory_capacity": 1,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 23
|
||||
},
|
||||
"failureCount": 77,
|
||||
"failureCount": 78,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 77,
|
||||
"unresolvedFailureCount": 76
|
||||
"total": 78,
|
||||
"unresolvedFailureCount": 77
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 38,
|
||||
@@ -4071,24 +4071,24 @@
|
||||
"decisionSuccessRate": 0.3333,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"ambiguous_runtime": 8,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 11,
|
||||
"failureRate": 0.8462,
|
||||
"failureCount": 12,
|
||||
"failureRate": 0.8571,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T01:42:34.770281+00:00",
|
||||
"lastTerminalAt": "2026-09-10T01:50:54.936003+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.1538,
|
||||
"successRate": 0.1429,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 13,
|
||||
"unresolvedFailureCount": 7
|
||||
"total": 14,
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
@@ -4279,13 +4279,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 9
|
||||
"ambiguous_runtime": 10
|
||||
},
|
||||
"failureCount": 9,
|
||||
"failureCount": 10,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T00:11:47.209836+00:00",
|
||||
"lastTerminalAt": "2026-09-10T01:50:54.936024+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4293,8 +4293,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 9
|
||||
"total": 10,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -6765,15 +6765,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1476,
|
||||
"totalRecords": 1560,
|
||||
"terminalRecords": 1478,
|
||||
"totalRecords": 1562,
|
||||
"totals": {
|
||||
"attributableFailureCount": 390,
|
||||
"decisionFailureRate": 0.8904,
|
||||
"decisionSuccessRate": 0.1096,
|
||||
"decisionTotal": 438,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 269,
|
||||
"ambiguous_runtime": 271,
|
||||
"backend_operator": 25,
|
||||
"framework_architecture_unsupported": 266,
|
||||
"memory_capacity": 11,
|
||||
@@ -6785,21 +6785,21 @@
|
||||
"参数/模板问题": 94,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1428,
|
||||
"failureCount": 1430,
|
||||
"failureRate": 0.9675,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 48,
|
||||
"successRate": 0.0325,
|
||||
"total": 1476,
|
||||
"unresolvedFailureCount": 1036
|
||||
"total": 1478,
|
||||
"unresolvedFailureCount": 1038
|
||||
},
|
||||
"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。",
|
||||
@@ -6807,7 +6807,7 @@
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU 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。",
|
||||
@@ -6828,6 +6828,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1560,
|
||||
"summarizedRecords": 1562,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -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": "2026-09-10T01:50:54.936003+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:49:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481654", "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": "2026-09-10T01:50:54.936024+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:43:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4596146", "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": "2026-09-10T01:42:34.770281+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:37:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481718", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T01:16:26.008857+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505087", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T01:16:26.008867+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505110", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -296,5 +298,3 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "", "lastSyncTime": "2026-09-07T05:18:43.228836+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Thinking-SFT", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:09:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4152438", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-07T05:05:30.903852+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:05:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4082915", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T05:05:30.903823+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T04:57:23+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4461505", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_text"], "framework": "", "lastSyncTime": "2026-09-07T04:51:27.989190+00:00", "modelId": "ValueFX/Qwen3.8-27B-CCCP-S", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T04:49:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4218096", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["RWKV7ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-07T04:34:12.697096+00:00", "modelId": "fla-hub/rwkv7-7.2B-g0", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T04:19:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079209", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user