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

state: generation 17703 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-28 03:24:55 +00:00
parent 17f8d62f89
commit d881f84e15
10 changed files with 1815 additions and 1772 deletions
Download Patch File Download Diff File Expand all files Collapse all files

217
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-27T21:37:17.329347+00:00",
"lastSyncTime": "2026-09-27T21:37:17.059954+00:00",
"generatedAt": "2026-09-28T03:23:38.538672+00:00",
"lastSyncTime": "2026-09-28T03:23:37.959151+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3818,15 +3818,15 @@
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm-customized",
"pendingCount": 0,
@@ -3836,7 +3836,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
@@ -3845,25 +3845,25 @@
"decisionSuccessRate": 0.3636,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 40,
"ambiguous_runtime": 41,
"framework_architecture_unsupported": 11,
"model_load": 3,
"platform_infrastructure": 1,
"参数/模板问题": 1,
"验证失败": 3
},
"failureCount": 59,
"failureRate": 0.8806,
"failureCount": 60,
"failureRate": 0.8824,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 8,
"successRate": 0.1194,
"successRate": 0.1176,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 67,
"unresolvedFailureCount": 44
"total": 68,
"unresolvedFailureCount": 45
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 24,
@@ -5987,26 +5987,26 @@
"unresolvedFailureCount": 1634
},
"vllm-customized": {
"attributableFailureCount": 13,
"attributableFailureCount": 14,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 13,
"decisionTotal": 14,
"failureBreakdown": {
"ambiguous_runtime": 46,
"framework_architecture_unsupported": 9,
"framework_architecture_unsupported": 10,
"model_load": 3,
"platform_infrastructure": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 5
},
"failureCount": 66,
"failureCount": 67,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 66,
"total": 67,
"unresolvedFailureCount": 51
},
"vllm-mlu": {
@@ -6015,7 +6015,7 @@
"decisionSuccessRate": 0.4167,
"decisionTotal": 48,
"failureBreakdown": {
"ambiguous_runtime": 87,
"ambiguous_runtime": 88,
"framework_architecture_unsupported": 22,
"model_load": 5,
"platform_infrastructure": 1,
@@ -6023,15 +6023,15 @@
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 123,
"failureRate": 0.8601,
"failureCount": 124,
"failureRate": 0.8611,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 20,
"successRate": 0.1399,
"total": 143,
"unresolvedFailureCount": 94
"successRate": 0.1389,
"total": 144,
"unresolvedFailureCount": 95
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 55,
@@ -6134,7 +6134,7 @@
"unresolvedFailureCount": 197
}
},
"generatedAt": "2026-09-27T21:37:17.317408+00:00",
"generatedAt": "2026-09-28T03:23:38.526090+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6221,15 +6221,15 @@
"unresolvedFailureCount": 554
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 744,
"decisionFailureRate": 0.9106,
"decisionSuccessRate": 0.0894,
"decisionTotal": 817,
"attributableFailureCount": 745,
"decisionFailureRate": 0.9108,
"decisionSuccessRate": 0.0892,
"decisionTotal": 818,
"failureBreakdown": {
"ambiguous_runtime": 503,
"ambiguous_runtime": 504,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 297,
"framework_architecture_unsupported": 298,
"memory_capacity": 219,
"model_load": 7,
"platform_infrastructure": 16,
@@ -6239,15 +6239,15 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1605,
"failureCount": 1607,
"failureRate": 0.9565,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 73,
"successRate": 0.0435,
"total": 1678,
"unresolvedFailureCount": 845
"total": 1680,
"unresolvedFailureCount": 846
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 60,
@@ -10552,6 +10552,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation|nemotron_h|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"modelType": "nemotron_h",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation|phi3|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -10927,9 +10950,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "phi3",
@@ -10941,8 +10964,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|plamo3|none": {
"attributableFailureCount": 0,
@@ -22935,10 +22958,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 6,
"参数/模板问题": 1
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -22950,8 +22973,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 7,
"unresolvedFailureCount": 7
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 1,
@@ -24005,6 +24028,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|phi3|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-28T03:23:37.959151+00:00",
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -24230,31 +24278,6 @@
"total": 4,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-21T23:49:30.866184+00:00",
"modelType": "llama",
"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": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|minicpm|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -32944,6 +32967,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation|nemotron_h|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"loadSizeLog2Bucket": 34,
"modelType": "nemotron_h",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation|phi3|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -33455,9 +33502,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 31,
@@ -33470,8 +33517,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|phi3|compressed-tensors|32": {
"attributableFailureCount": 0,
@@ -51385,20 +51432,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17065,
"totalRecords": 17286,
"terminalRecords": 17067,
"totalRecords": 17288,
"totals": {
"attributableFailureCount": 6114,
"attributableFailureCount": 6115,
"decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364,
"decisionTotal": 7080,
"decisionTotal": 7081,
"failureBreakdown": {
"ambiguous_runtime": 4424,
"ambiguous_runtime": 4425,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 322,
"framework_architecture_unsupported": 2171,
"framework_architecture_unsupported": 2172,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 938,
@@ -51409,15 +51456,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16099,
"failureCount": 16101,
"failureRate": 0.9434,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 938,
"successCount": 966,
"successRate": 0.0566,
"total": 17065,
"unresolvedFailureCount": 9047
"total": 17067,
"unresolvedFailureCount": 9048
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -51425,15 +51472,15 @@
"GPU Ascend_910-b4 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 MetaX_c-500 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 Vastai_va16 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-b3 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 Biren_166m 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-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 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。",
"组合 Ascend_910-b3|vllm_tokenizer_patch|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-b3|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|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51457,6 +51504,7 @@
"组合 Cambricon_mlu-370-x4|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|transformers|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。",
"组合 Vastai_va16|vllm_fix_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 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|llamacpp|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-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51470,11 +51518,10 @@
"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 Kunlunxin_p-800|vllm_tokenizer_patch|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|llamacpp|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_fix_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 Iluvatar_bi-150|llamacpp|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": 17286,
"summarizedRecords": 17288,
"version": 1
}