state: generation 6298 (cycle)

This commit is contained in:
2026-09-12 17:18:51 +00:00
parent 88d951925d
commit 7ce9eff94f
9 changed files with 1991 additions and 2017 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T17:06:35.144805+00:00",
"lastSyncTime": "2026-09-12T17:06:34.916681+00:00",
"generatedAt": "2026-09-12T17:16:50.134307+00:00",
"lastSyncTime": "2026-09-12T17:16:49.913530+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1318,17 +1318,17 @@
"architectureSignature": "model_type:nemotron_h",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-07T03:49:21+00:00",
"expiresAt": "2026-10-12T17:15:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-07T03:49:21+00:00",
"latestFailureAt": "2026-09-12T17:15:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "nemotron_h",
"sourceModelIds": [
"nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15"
"primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8"
],
"sourceTaskIds": [
"4609084"
"4543650"
],
"targetGpu": "Vastai_va16",
"taskType": "text-generation"
@@ -2260,17 +2260,17 @@
"unresolvedFailureCount": 2
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 46,
"attributableFailureCount": 47,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 46,
"decisionTotal": 47,
"failureBreakdown": {
"ambiguous_runtime": 61,
"framework_architecture_unsupported": 40,
"framework_architecture_unsupported": 41,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 107,
"failureCount": 108,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2280,7 +2280,7 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 107,
"total": 108,
"unresolvedFailureCount": 61
},
"hygon_k100-ai|llamacpp|text-generation": {
@@ -2440,14 +2440,14 @@
"unresolvedFailureCount": 866
},
"vllm": {
"attributableFailureCount": 278,
"decisionFailureRate": 0.9893,
"decisionSuccessRate": 0.0107,
"decisionTotal": 281,
"attributableFailureCount": 279,
"decisionFailureRate": 0.9894,
"decisionSuccessRate": 0.0106,
"decisionTotal": 282,
"failureBreakdown": {
"ambiguous_runtime": 200,
"backend_operator": 34,
"framework_architecture_unsupported": 192,
"framework_architecture_unsupported": 193,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2456,14 +2456,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 503,
"failureCount": 504,
"failureRate": 0.9941,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0059,
"total": 506,
"total": 507,
"unresolvedFailureCount": 224
},
"vllm-mlu": {
@@ -2568,7 +2568,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T17:06:35.140682+00:00",
"generatedAt": "2026-09-12T17:16:50.130271+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 28,
@@ -2852,26 +2852,26 @@
"unresolvedFailureCount": 42
},
"Vastai_va16": {
"attributableFailureCount": 49,
"decisionFailureRate": 0.7903,
"decisionSuccessRate": 0.2097,
"decisionTotal": 62,
"attributableFailureCount": 50,
"decisionFailureRate": 0.7937,
"decisionSuccessRate": 0.2063,
"decisionTotal": 63,
"failureBreakdown": {
"ambiguous_runtime": 63,
"framework_architecture_unsupported": 42,
"framework_architecture_unsupported": 43,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 255,
"failureRate": 0.9515,
"failureCount": 256,
"failureRate": 0.9517,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0485,
"total": 268,
"successRate": 0.0483,
"total": 269,
"unresolvedFailureCount": 206
},
"hygon_k100-ai": {
@@ -4591,9 +4591,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 13
"ambiguous_runtime": 12
},
"failureCount": 13,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -4605,8 +4605,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 13
"total": 12,
"unresolvedFailureCount": 12
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
@@ -4791,21 +4791,21 @@
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 2
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 3
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T10:56:57.011705+00:00",
"lastTerminalAt": "2026-09-12T17:16:49.913530+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4814,7 +4814,7 @@
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 18
"unresolvedFailureCount": 17
},
"hygon_k100-ai|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4947,31 +4947,6 @@
"total": 3,
"unresolvedFailureCount": 3
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-09T14:00:25.508497+00:00",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -7279,17 +7254,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1730,
"totalRecords": 1817,
"terminalRecords": 1731,
"totalRecords": 1818,
"totals": {
"attributableFailureCount": 490,
"decisionFailureRate": 0.8958,
"decisionSuccessRate": 0.1042,
"decisionTotal": 547,
"attributableFailureCount": 491,
"decisionFailureRate": 0.896,
"decisionSuccessRate": 0.104,
"decisionTotal": 548,
"failureBreakdown": {
"ambiguous_runtime": 405,
"backend_operator": 42,
"framework_architecture_unsupported": 303,
"framework_architecture_unsupported": 304,
"memory_capacity": 11,
"model_load": 72,
"platform_infrastructure": 4,
@@ -7299,20 +7274,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1673,
"failureCount": 1674,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0329,
"total": 1730,
"total": 1731,
"unresolvedFailureCount": 1179
},
"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。",
@@ -7321,7 +7297,6 @@
"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。",
@@ -7343,6 +7318,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1817,
"summarizedRecords": 1818,
"version": 1
}