state: generation 6413 (cycle)

This commit is contained in:
2026-09-12 23:28:31 +00:00
parent c4e02554b9
commit b32a850695
9 changed files with 2222 additions and 2242 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T23:00:14.027433+00:00",
"lastSyncTime": "2026-09-12T23:00:13.841305+00:00",
"generatedAt": "2026-09-12T23:26:15.863219+00:00",
"lastSyncTime": "2026-09-12T23:26:15.638629+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -348,17 +348,19 @@
"ascend_910-b4|vllm|text-generation|model_type:rwkv7": {
"architectureSignature": "model_type:rwkv7",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-09T19:59:21+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-12T23:23:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-09T19:59:21+00:00",
"latestFailureAt": "2026-09-12T23:23:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "rwkv7",
"sourceModelIds": [
"RWKV/RWKV7-2.9B-20260805",
"RWKV/RWKV7-1.5B-20260805"
],
"sourceTaskIds": [
"4582844",
"4577671"
],
"targetGpu": "Ascend_910-b4",
@@ -1585,18 +1587,18 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 43,
"attributableFailureCount": 44,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 43,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 35,
"framework_architecture_unsupported": 39,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 78,
"failureCount": 79,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1606,7 +1608,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 78,
"total": 79,
"unresolvedFailureCount": 35
},
"Biren_166m|unknown|text-generation": {
@@ -1615,7 +1617,7 @@
"decisionSuccessRate": 0.0345,
"decisionTotal": 29,
"failureBreakdown": {
"ambiguous_runtime": 27,
"ambiguous_runtime": 28,
"backend_operator": 4,
"framework_architecture_unsupported": 20,
"memory_capacity": 1,
@@ -1623,18 +1625,18 @@
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 82,
"failureRate": 0.988,
"failureCount": 83,
"failureRate": 0.9881,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.012,
"successRate": 0.0119,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 83,
"unresolvedFailureCount": 54
"total": 84,
"unresolvedFailureCount": 55
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -2442,7 +2444,7 @@
"decisionSuccessRate": 0.2624,
"decisionTotal": 202,
"failureBreakdown": {
"ambiguous_runtime": 137,
"ambiguous_runtime": 138,
"backend_operator": 4,
"framework_architecture_unsupported": 94,
"memory_capacity": 5,
@@ -2452,25 +2454,25 @@
"参数/模板问题": 59,
"验证失败": 673
},
"failureCount": 1019,
"failureCount": 1020,
"failureRate": 0.9506,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 53,
"successRate": 0.0494,
"total": 1072,
"unresolvedFailureCount": 869
"total": 1073,
"unresolvedFailureCount": 870
},
"vllm": {
"attributableFailureCount": 282,
"attributableFailureCount": 283,
"decisionFailureRate": 0.9895,
"decisionSuccessRate": 0.0105,
"decisionTotal": 285,
"decisionTotal": 286,
"failureBreakdown": {
"ambiguous_runtime": 201,
"backend_operator": 34,
"framework_architecture_unsupported": 196,
"framework_architecture_unsupported": 197,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2479,14 +2481,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 508,
"failureCount": 509,
"failureRate": 0.9941,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0059,
"total": 511,
"total": 512,
"unresolvedFailureCount": 225
},
"vllm-mlu": {
@@ -2591,7 +2593,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T23:00:14.021225+00:00",
"generatedAt": "2026-09-12T23:26:15.857888+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 30,
@@ -2617,13 +2619,13 @@
"unresolvedFailureCount": 63
},
"Ascend_910-b4": {
"attributableFailureCount": 44,
"decisionFailureRate": 0.9565,
"decisionSuccessRate": 0.0435,
"decisionTotal": 46,
"attributableFailureCount": 45,
"decisionFailureRate": 0.9574,
"decisionSuccessRate": 0.0426,
"decisionTotal": 47,
"failureBreakdown": {
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 39,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 1,
"repository_structure": 1,
@@ -2631,14 +2633,14 @@
"参数/模板问题": 12,
"验证失败": 175
},
"failureCount": 267,
"failureCount": 268,
"failureRate": 0.9926,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0074,
"total": 269,
"total": 270,
"unresolvedFailureCount": 223
},
"Biren_166m": {
@@ -2647,7 +2649,7 @@
"decisionSuccessRate": 0.0312,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 27,
"ambiguous_runtime": 28,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2655,15 +2657,15 @@
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 85,
"failureRate": 0.9884,
"failureCount": 86,
"failureRate": 0.9885,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0116,
"total": 86,
"unresolvedFailureCount": 54
"successRate": 0.0115,
"total": 87,
"unresolvedFailureCount": 55
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 21,
@@ -4417,21 +4419,21 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 6
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 7
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T16:46:42.939263+00:00",
"lastTerminalAt": "2026-09-12T23:26:15.638604+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4440,7 +4442,7 @@
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 14
"unresolvedFailureCount": 13
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 8,
@@ -4450,16 +4452,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 9,
"ambiguous_runtime": 10,
"backend_operator": 4,
"framework_architecture_unsupported": 3,
"model_load": 1
},
"failureCount": 17,
"failureCount": 18,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T20:28:29.094162+00:00",
"lastTerminalAt": "2026-09-12T23:26:15.638629+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4467,8 +4469,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 9
"total": 18,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -4661,9 +4663,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 1
},
"failureCount": 3,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -4675,8 +4677,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 1,
"unresolvedFailureCount": 1
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
@@ -4943,31 +4945,6 @@
},
"recentProfileCombinationStats": {
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-10T18:58:50.012615+00:00",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
@@ -4979,8 +4956,8 @@
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-10T09:38:19.106782+00:00",
"modelType": "rwkv7",
"lastTerminalAt": "2026-09-10T18:58:50.012615+00:00",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7247,17 +7224,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1742,
"totalRecords": 1829,
"terminalRecords": 1744,
"totalRecords": 1831,
"totals": {
"attributableFailureCount": 497,
"decisionFailureRate": 0.8955,
"decisionSuccessRate": 0.1045,
"decisionTotal": 555,
"attributableFailureCount": 498,
"decisionFailureRate": 0.8957,
"decisionSuccessRate": 0.1043,
"decisionTotal": 556,
"failureBreakdown": {
"ambiguous_runtime": 409,
"ambiguous_runtime": 410,
"backend_operator": 42,
"framework_architecture_unsupported": 309,
"framework_architecture_unsupported": 310,
"memory_capacity": 11,
"model_load": 73,
"platform_infrastructure": 4,
@@ -7267,20 +7244,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1684,
"failureCount": 1686,
"failureRate": 0.9667,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 58,
"successRate": 0.0333,
"total": 1742,
"unresolvedFailureCount": 1183
"total": 1744,
"unresolvedFailureCount": 1184
},
"warnings": [
"GPU Ascend_910-b3 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 Sunrise_pt-200-x1 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 Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7289,7 +7267,6 @@
"GPU MetaX_c-500 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 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 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|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7312,6 +7289,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1829,
"summarizedRecords": 1831,
"version": 1
}