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

state: generation 7066 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-14 07:34:49 +00:00
parent 3a8a177748
commit 2b744f6aeb
7 changed files with 2451 additions and 1630 deletions
Download Patch File Download Diff File Expand all files Collapse all files

188
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-14T07:06:23.064894+00:00",
"lastSyncTime": "2026-09-14T07:06:22.844621+00:00",
"generatedAt": "2026-09-14T07:31:52.894119+00:00",
"lastSyncTime": "2026-09-14T07:31:50.924213+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -350,7 +350,7 @@
"ascend_910-b4|vllm|text-generation|model_type:rwkv7": {
"architectureSignature": "model_type:rwkv7",
"architectures": [],
"evidenceCount": 3,
"evidenceCount": 2,
"expiresAt": "2026-10-14T02:47:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-14T02:47:21+00:00",
@@ -359,13 +359,11 @@
"modelType": "rwkv7",
"sourceModelIds": [
"RWKV/RWKV7-13.3B-20260805",
"RWKV/RWKV7-2.9B-20260805",
"RWKV/RWKV7-1.5B-20260805"
"RWKV/RWKV7-2.9B-20260805"
],
"sourceTaskIds": [
"4493314",
"4582844",
"4577671"
"4582844"
],
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation"
@@ -1571,12 +1569,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 28,
"ambiguous_runtime": 29,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"tokenizer_compatibility": 1
},
"failureCount": 60,
"failureCount": 61,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1586,8 +1584,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 60,
"unresolvedFailureCount": 28
"total": 61,
"unresolvedFailureCount": 29
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1,
@@ -1728,28 +1726,28 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 21,
"decisionFailureRate": 0.913,
"decisionSuccessRate": 0.087,
"decisionTotal": 23,
"attributableFailureCount": 22,
"decisionFailureRate": 0.9167,
"decisionSuccessRate": 0.0833,
"decisionTotal": 24,
"failureBreakdown": {
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 19,
"framework_architecture_unsupported": 20,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 96,
"failureRate": 0.9796,
"failureCount": 97,
"failureRate": 0.9798,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0204,
"successRate": 0.0202,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 98,
"total": 99,
"unresolvedFailureCount": 75
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
@@ -1982,30 +1980,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 95,
"decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364,
"decisionTotal": 110,
"attributableFailureCount": 96,
"decisionFailureRate": 0.8649,
"decisionSuccessRate": 0.1351,
"decisionTotal": 111,
"failureBreakdown": {
"ambiguous_runtime": 23,
"framework_architecture_unsupported": 52,
"framework_architecture_unsupported": 53,
"memory_capacity": 1,
"model_load": 42,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 168,
"failureRate": 0.918,
"failureCount": 169,
"failureRate": 0.9185,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 15,
"successRate": 0.082,
"successRate": 0.0815,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 183,
"total": 184,
"unresolvedFailureCount": 72
},
"Iluvatar_mrv-100|vllm|text-generation": {
@@ -2510,14 +2508,14 @@
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 156,
"decisionFailureRate": 0.7429,
"decisionSuccessRate": 0.2571,
"decisionTotal": 210,
"attributableFailureCount": 158,
"decisionFailureRate": 0.7453,
"decisionSuccessRate": 0.2547,
"decisionTotal": 212,
"failureBreakdown": {
"ambiguous_runtime": 147,
"backend_operator": 4,
"framework_architecture_unsupported": 100,
"framework_architecture_unsupported": 102,
"memory_capacity": 5,
"model_load": 44,
"platform_infrastructure": 1,
@@ -2525,14 +2523,14 @@
"参数/模板问题": 61,
"验证失败": 673
},
"failureCount": 1038,
"failureRate": 0.9505,
"failureCount": 1040,
"failureRate": 0.9506,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 54,
"successRate": 0.0495,
"total": 1092,
"successRate": 0.0494,
"total": 1094,
"unresolvedFailureCount": 881
},
"vllm": {
@@ -2541,7 +2539,7 @@
"decisionSuccessRate": 0.0096,
"decisionTotal": 312,
"failureBreakdown": {
"ambiguous_runtime": 203,
"ambiguous_runtime": 204,
"backend_operator": 34,
"framework_architecture_unsupported": 221,
"memory_capacity": 7,
@@ -2552,15 +2550,15 @@
"tokenizer_compatibility": 7,
"参数/模板问题": 30
},
"failureCount": 543,
"failureCount": 544,
"failureRate": 0.9945,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0055,
"total": 546,
"unresolvedFailureCount": 233
"total": 547,
"unresolvedFailureCount": 234
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2666,7 +2664,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-14T07:06:23.057995+00:00",
"generatedAt": "2026-09-14T07:31:52.889348+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 32,
@@ -2674,22 +2672,22 @@
"decisionSuccessRate": 0.0303,
"decisionTotal": 33,
"failureBreakdown": {
"ambiguous_runtime": 28,
"ambiguous_runtime": 29,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 95,
"failureRate": 0.9896,
"failureCount": 96,
"failureRate": 0.9897,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0104,
"total": 96,
"unresolvedFailureCount": 63
"successRate": 0.0103,
"total": 97,
"unresolvedFailureCount": 64
},
"Ascend_910-b4": {
"attributableFailureCount": 47,
@@ -2741,25 +2739,25 @@
"unresolvedFailureCount": 56
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 21,
"decisionFailureRate": 0.913,
"decisionSuccessRate": 0.087,
"decisionTotal": 23,
"attributableFailureCount": 22,
"decisionFailureRate": 0.9167,
"decisionSuccessRate": 0.0833,
"decisionTotal": 24,
"failureBreakdown": {
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 19,
"framework_architecture_unsupported": 20,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 96,
"failureRate": 0.9796,
"failureCount": 97,
"failureRate": 0.9798,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0204,
"total": 98,
"successRate": 0.0202,
"total": 99,
"unresolvedFailureCount": 75
},
"Cambricon_mlu-370-x8": {
@@ -2830,27 +2828,27 @@
"unresolvedFailureCount": 46
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 98,
"decisionFailureRate": 0.8673,
"decisionSuccessRate": 0.1327,
"decisionTotal": 113,
"attributableFailureCount": 99,
"decisionFailureRate": 0.8684,
"decisionSuccessRate": 0.1316,
"decisionTotal": 114,
"failureBreakdown": {
"ambiguous_runtime": 23,
"framework_architecture_unsupported": 54,
"framework_architecture_unsupported": 55,
"memory_capacity": 1,
"model_load": 43,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 171,
"failureRate": 0.9194,
"failureCount": 172,
"failureRate": 0.9198,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 15,
"successRate": 0.0806,
"total": 186,
"successRate": 0.0802,
"total": 187,
"unresolvedFailureCount": 72
},
"Kunlunxin_p-800": {
@@ -4802,7 +4800,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T02:14:40.319417+00:00",
"lastTerminalAt": "2026-09-14T07:31:50.924177+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4893,21 +4891,21 @@
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 1
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 2
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T04:23:07.613289+00:00",
"lastTerminalAt": "2026-09-14T07:31:50.924213+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4916,7 +4914,7 @@
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 19
"unresolvedFailureCount": 18
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -4926,10 +4924,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 13,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 1
},
"failureCount": 14,
"failureCount": 12,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -4941,8 +4939,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 13
"total": 12,
"unresolvedFailureCount": 11
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
@@ -5024,7 +5022,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 10,
"consecutiveFailures": 3,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
@@ -5038,7 +5036,7 @@
"failureRate": 0.75,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T21:45:41.613474+00:00",
"lastTerminalAt": "2026-09-14T07:31:50.924203+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -8029,17 +8027,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1812,
"totalRecords": 1905,
"terminalRecords": 1815,
"totalRecords": 1908,
"totals": {
"attributableFailureCount": 540,
"decisionFailureRate": 0.9015,
"decisionSuccessRate": 0.0985,
"decisionTotal": 599,
"attributableFailureCount": 542,
"decisionFailureRate": 0.9018,
"decisionSuccessRate": 0.0982,
"decisionTotal": 601,
"failureBreakdown": {
"ambiguous_runtime": 425,
"ambiguous_runtime": 426,
"backend_operator": 43,
"framework_architecture_unsupported": 343,
"framework_architecture_unsupported": 345,
"memory_capacity": 12,
"model_load": 75,
"platform_infrastructure": 6,
@@ -8049,15 +8047,15 @@
"参数/模板问题": 109,
"验证失败": 673
},
"failureCount": 1753,
"failureRate": 0.9674,
"failureCount": 1756,
"failureRate": 0.9675,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 59,
"successRate": 0.0326,
"total": 1812,
"unresolvedFailureCount": 1207
"successRate": 0.0325,
"total": 1815,
"unresolvedFailureCount": 1208
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -8095,6 +8093,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1905,
"summarizedRecords": 1908,
"version": 1
}