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

state: generation 5323 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 19:19:48 +00:00
parent 4485b1c379
commit b302da72be
9 changed files with 2046 additions and 2071 deletions
Download Patch File Download Diff File Expand all files Collapse all files

135
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T19:08:02.247819+00:00",
"lastSyncTime": "2026-09-10T19:08:02.004199+00:00",
"generatedAt": "2026-09-10T19:17:57.140826+00:00",
"lastSyncTime": "2026-09-10T19:17:56.906562+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1791,30 +1791,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 73,
"decisionFailureRate": 0.8795,
"decisionSuccessRate": 0.1205,
"decisionTotal": 83,
"attributableFailureCount": 74,
"decisionFailureRate": 0.881,
"decisionSuccessRate": 0.119,
"decisionTotal": 84,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 25,
"model_load": 26,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 140,
"failureRate": 0.9333,
"failureCount": 141,
"failureRate": 0.9338,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0667,
"successRate": 0.0662,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 150,
"total": 151,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2292,29 +2292,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 127,
"decisionFailureRate": 0.7257,
"decisionSuccessRate": 0.2743,
"decisionTotal": 175,
"attributableFailureCount": 128,
"decisionFailureRate": 0.7273,
"decisionSuccessRate": 0.2727,
"decisionTotal": 176,
"failureBreakdown": {
"ambiguous_runtime": 123,
"backend_operator": 4,
"framework_architecture_unsupported": 88,
"memory_capacity": 5,
"model_load": 27,
"model_load": 28,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 980,
"failureRate": 0.9533,
"failureCount": 981,
"failureRate": 0.9534,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0467,
"total": 1028,
"successRate": 0.0466,
"total": 1029,
"unresolvedFailureCount": 852
},
"vllm": {
@@ -2445,7 +2445,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T19:08:02.242490+00:00",
"generatedAt": "2026-09-10T19:17:57.136465+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2608,27 +2608,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 73,
"decisionFailureRate": 0.8795,
"decisionSuccessRate": 0.1205,
"decisionTotal": 83,
"attributableFailureCount": 74,
"decisionFailureRate": 0.881,
"decisionSuccessRate": 0.119,
"decisionTotal": 84,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 25,
"model_load": 26,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 140,
"failureRate": 0.9333,
"failureCount": 141,
"failureRate": 0.9338,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0667,
"total": 150,
"successRate": 0.0662,
"total": 151,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800": {
@@ -4165,18 +4165,18 @@
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 4,
"framework_architecture_unsupported": 3,
"参数/模板问题": 1
},
"failureCount": 10,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4188,7 +4188,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 10,
"total": 9,
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
@@ -4271,22 +4271,22 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 6,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 8,
"model_load": 7,
"framework_architecture_unsupported": 7,
"model_load": 8,
"platform_infrastructure": 1
},
"failureCount": 17,
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-10T19:08:02.004176+00:00",
"lastTerminalAt": "2026-09-10T19:17:56.906562+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4684,31 +4684,6 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|rwkv7|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-09T20:13:30.044188+00:00",
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -7073,19 +7048,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1624,
"totalRecords": 1711,
"terminalRecords": 1625,
"totalRecords": 1712,
"totals": {
"attributableFailureCount": 422,
"decisionFailureRate": 0.8903,
"decisionSuccessRate": 0.1097,
"decisionTotal": 474,
"attributableFailureCount": 423,
"decisionFailureRate": 0.8905,
"decisionSuccessRate": 0.1095,
"decisionTotal": 475,
"failureBreakdown": {
"ambiguous_runtime": 375,
"backend_operator": 40,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
"model_load": 49,
"model_load": 50,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -7093,31 +7068,30 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1572,
"failureCount": 1573,
"failureRate": 0.968,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 52,
"successRate": 0.032,
"total": 1624,
"total": 1625,
"unresolvedFailureCount": 1146
},
"warnings": [
"GPU Ascend_910-b3 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 Iluvatar_mrv-100 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 MetaX_c-500 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 Iluvatar_bi-150 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 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。",
"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-x4|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 Mthreads_s4000|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 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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7132,10 +7106,11 @@
"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 Iluvatar_bi-150|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 Vastai_va16|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 Cambricon_mlu-370-x4|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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1711,
"summarizedRecords": 1712,
"version": 1
}