CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 5093 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 09:22:52 +00:00
parent 7e21cdff9b
commit a976778853
9 changed files with 2055 additions and 2055 deletions
Download Patch File Download Diff File Expand all files Collapse all files

136
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T08:54:23.705220+00:00",
"lastSyncTime": "2026-09-10T08:54:23.346315+00:00",
"generatedAt": "2026-09-10T09:20:50.642259+00:00",
"lastSyncTime": "2026-09-10T09:20:50.207436+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1390,12 +1390,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 26,
"failureBreakdown": {
"ambiguous_runtime": 22,
"ambiguous_runtime": 23,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"tokenizer_compatibility": 1
},
"failureCount": 48,
"failureCount": 49,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1405,8 +1405,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 48,
"unresolvedFailureCount": 22
"total": 49,
"unresolvedFailureCount": 23
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1,
@@ -1503,7 +1503,7 @@
"decisionSuccessRate": 0.04,
"decisionTotal": 25,
"failureBreakdown": {
"ambiguous_runtime": 24,
"ambiguous_runtime": 26,
"backend_operator": 2,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
@@ -1511,18 +1511,18 @@
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 75,
"failureRate": 0.9868,
"failureCount": 77,
"failureRate": 0.9872,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0132,
"successRate": 0.0128,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 76,
"unresolvedFailureCount": 51
"total": 78,
"unresolvedFailureCount": 53
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 1,
@@ -2300,7 +2300,7 @@
"decisionSuccessRate": 0.284,
"decisionTotal": 169,
"failureBreakdown": {
"ambiguous_runtime": 113,
"ambiguous_runtime": 115,
"backend_operator": 2,
"framework_architecture_unsupported": 87,
"memory_capacity": 5,
@@ -2309,15 +2309,15 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 963,
"failureRate": 0.9525,
"failureCount": 965,
"failureRate": 0.9526,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 48,
"successRate": 0.0475,
"total": 1011,
"unresolvedFailureCount": 842
"successRate": 0.0474,
"total": 1013,
"unresolvedFailureCount": 844
},
"vllm": {
"attributableFailureCount": 234,
@@ -2325,7 +2325,7 @@
"decisionSuccessRate": 0.0043,
"decisionTotal": 235,
"failureBreakdown": {
"ambiguous_runtime": 154,
"ambiguous_runtime": 155,
"backend_operator": 28,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2336,15 +2336,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 410,
"failureCount": 411,
"failureRate": 0.9976,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0024,
"total": 411,
"unresolvedFailureCount": 175
"total": 412,
"unresolvedFailureCount": 176
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T08:54:23.700725+00:00",
"generatedAt": "2026-09-10T09:20:50.635463+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2455,22 +2455,22 @@
"decisionSuccessRate": 0.037,
"decisionTotal": 27,
"failureBreakdown": {
"ambiguous_runtime": 22,
"ambiguous_runtime": 23,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 83,
"failureRate": 0.9881,
"failureCount": 84,
"failureRate": 0.9882,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0119,
"total": 84,
"unresolvedFailureCount": 57
"successRate": 0.0118,
"total": 85,
"unresolvedFailureCount": 58
},
"Ascend_910-b4": {
"attributableFailureCount": 38,
@@ -2503,7 +2503,7 @@
"decisionSuccessRate": 0.0385,
"decisionTotal": 26,
"failureBreakdown": {
"ambiguous_runtime": 24,
"ambiguous_runtime": 26,
"backend_operator": 2,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
@@ -2511,15 +2511,15 @@
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 76,
"failureRate": 0.987,
"failureCount": 78,
"failureRate": 0.9873,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.013,
"total": 77,
"unresolvedFailureCount": 51
"successRate": 0.0127,
"total": 79,
"unresolvedFailureCount": 53
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 20,
@@ -3971,14 +3971,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 16,
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 3
},
"failureCount": 19,
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T06:40:56.094753+00:00",
"lastTerminalAt": "2026-09-10T09:20:50.207436+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -3986,8 +3986,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 19,
"unresolvedFailureCount": 16
"total": 20,
"unresolvedFailureCount": 17
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1,
@@ -4048,51 +4048,51 @@
"decisionSuccessRate": 0.1429,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 10,
"backend_operator": 2,
"framework_architecture_unsupported": 3,
"model_load": 1
},
"failureCount": 14,
"failureRate": 0.9333,
"failureCount": 16,
"failureRate": 0.9412,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T06:11:26.144205+00:00",
"lastTerminalAt": "2026-09-10T09:20:50.207399+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0667,
"successRate": 0.0588,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 15,
"unresolvedFailureCount": 8
"total": 17,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.75,
"decisionSuccessRate": 0.25,
"decisionTotal": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 2,
"tokenizer_compatibility": 1
},
"failureCount": 11,
"failureRate": 0.9167,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T07:29:02.941680+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0833,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 12,
"total": 11,
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
@@ -4359,7 +4359,7 @@
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -4369,11 +4369,11 @@
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successCount": 1,
"successRate": 1.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation": {
@@ -6986,15 +6986,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1546,
"totalRecords": 1633,
"terminalRecords": 1549,
"totalRecords": 1636,
"totals": {
"attributableFailureCount": 404,
"decisionFailureRate": 0.8879,
"decisionSuccessRate": 0.1121,
"decisionTotal": 455,
"failureBreakdown": {
"ambiguous_runtime": 321,
"ambiguous_runtime": 324,
"backend_operator": 33,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -7006,21 +7006,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1495,
"failureRate": 0.967,
"failureCount": 1498,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 51,
"successRate": 0.033,
"total": 1546,
"unresolvedFailureCount": 1089
"successRate": 0.0329,
"total": 1549,
"unresolvedFailureCount": 1092
},
"warnings": [
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -7028,7 +7028,7 @@
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7049,6 +7049,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1633,
"summarizedRecords": 1636,
"version": 1
}