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

state: generation 6060 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-12 06:11:05 +00:00
parent 58dd78c756
commit a3902a3d6d
9 changed files with 2232 additions and 2280 deletions
Download Patch File Download Diff File Expand all files Collapse all files

142
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T05:51:39.514849+00:00",
"lastSyncTime": "2026-09-12T05:51:39.310788+00:00",
"generatedAt": "2026-09-12T06:09:22.494138+00:00",
"lastSyncTime": "2026-09-12T06:09:22.250742+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1960,29 +1960,29 @@
"unresolvedFailureCount": 56
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 46,
"decisionFailureRate": 0.9388,
"decisionSuccessRate": 0.0612,
"decisionTotal": 49,
"attributableFailureCount": 47,
"decisionFailureRate": 0.94,
"decisionSuccessRate": 0.06,
"decisionTotal": 50,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 27,
"framework_architecture_unsupported": 14,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 9
},
"failureCount": 62,
"failureRate": 0.9538,
"failureCount": 63,
"failureRate": 0.9545,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0462,
"successRate": 0.0455,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 65,
"total": 66,
"unresolvedFailureCount": 16
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2375,14 +2375,14 @@
"unresolvedFailureCount": 862
},
"vllm": {
"attributableFailureCount": 255,
"attributableFailureCount": 256,
"decisionFailureRate": 0.9884,
"decisionSuccessRate": 0.0116,
"decisionTotal": 258,
"decisionTotal": 259,
"failureBreakdown": {
"ambiguous_runtime": 195,
"backend_operator": 33,
"framework_architecture_unsupported": 174,
"framework_architecture_unsupported": 175,
"memory_capacity": 6,
"model_load": 23,
"platform_infrastructure": 1,
@@ -2391,14 +2391,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 475,
"failureCount": 476,
"failureRate": 0.9937,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0063,
"total": 478,
"total": 479,
"unresolvedFailureCount": 219
},
"vllm-mlu": {
@@ -2503,7 +2503,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T05:51:39.509102+00:00",
"generatedAt": "2026-09-12T06:09:22.489414+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2712,27 +2712,27 @@
"unresolvedFailureCount": 90
},
"MetaX_c-500": {
"attributableFailureCount": 46,
"decisionFailureRate": 0.7931,
"decisionSuccessRate": 0.2069,
"decisionTotal": 58,
"attributableFailureCount": 47,
"decisionFailureRate": 0.7966,
"decisionSuccessRate": 0.2034,
"decisionTotal": 59,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 27,
"framework_architecture_unsupported": 14,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 17,
"验证失败": 48
},
"failureCount": 118,
"failureRate": 0.9077,
"failureCount": 119,
"failureRate": 0.9084,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 12,
"successRate": 0.0923,
"total": 130,
"successRate": 0.0916,
"total": 131,
"unresolvedFailureCount": 72
},
"Mthreads_s4000": {
@@ -4519,21 +4519,21 @@
"unresolvedFailureCount": 19
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 5
"framework_architecture_unsupported": 6
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-08T22:32:41.015088+00:00",
"lastTerminalAt": "2026-09-12T06:09:22.250742+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4541,7 +4541,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -4749,31 +4749,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T03:01:10.207494+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 7,
"consecutiveFailures": 7,
@@ -5104,31 +5079,6 @@
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|zaya|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-patch-tokenizer",
"lastTerminalAt": "2026-09-09T03:01:10.207494+00:00",
"modelType": "zaya",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
}
},
"sizedProfileCombinationStats": {
@@ -7239,17 +7189,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1689,
"totalRecords": 1776,
"terminalRecords": 1690,
"totalRecords": 1777,
"totals": {
"attributableFailureCount": 460,
"decisionFailureRate": 0.8915,
"decisionSuccessRate": 0.1085,
"decisionTotal": 516,
"attributableFailureCount": 461,
"decisionFailureRate": 0.8917,
"decisionSuccessRate": 0.1083,
"decisionTotal": 517,
"failureBreakdown": {
"ambiguous_runtime": 395,
"backend_operator": 41,
"framework_architecture_unsupported": 281,
"framework_architecture_unsupported": 282,
"memory_capacity": 11,
"model_load": 67,
"platform_infrastructure": 4,
@@ -7259,21 +7209,20 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1633,
"failureRate": 0.9668,
"failureCount": 1634,
"failureRate": 0.9669,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.0332,
"total": 1689,
"successRate": 0.0331,
"total": 1690,
"unresolvedFailureCount": 1169
},
"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。",
@@ -7282,6 +7231,7 @@
"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。",
@@ -7303,6 +7253,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1776,
"summarizedRecords": 1777,
"version": 1
}