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

state: generation 4821 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-09 22:51:14 +00:00
parent 69283ba38e
commit 15c597dc7e
9 changed files with 1917 additions and 1915 deletions
Download Patch File Download Diff File Expand all files Collapse all files

79
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-09T22:41:00.047359+00:00",
"lastSyncTime": "2026-09-09T22:40:59.810547+00:00",
"generatedAt": "2026-09-09T22:49:15.615221+00:00",
"lastSyncTime": "2026-09-09T22:49:15.213972+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1473,13 +1473,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 18,
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 55,
"failureCount": 57,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1489,8 +1489,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 55,
"unresolvedFailureCount": 18
"total": 57,
"unresolvedFailureCount": 20
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 24,
@@ -2320,7 +2320,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 225,
"failureBreakdown": {
"ambiguous_runtime": 116,
"ambiguous_runtime": 118,
"backend_operator": 20,
"framework_architecture_unsupported": 168,
"memory_capacity": 6,
@@ -2331,15 +2331,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 363,
"failureCount": 365,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 363,
"unresolvedFailureCount": 137
"total": 365,
"unresolvedFailureCount": 139
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2442,7 +2442,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-09T22:41:00.042625+00:00",
"generatedAt": "2026-09-09T22:49:15.610998+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2473,7 +2473,7 @@
"decisionSuccessRate": 0.05,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 19,
"ambiguous_runtime": 21,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"model_load": 1,
@@ -2482,15 +2482,15 @@
"参数/模板问题": 11,
"验证失败": 175
},
"failureCount": 243,
"failureRate": 0.9918,
"failureCount": 245,
"failureRate": 0.9919,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0082,
"total": 245,
"unresolvedFailureCount": 205
"successRate": 0.0081,
"total": 247,
"unresolvedFailureCount": 207
},
"Biren_166m": {
"attributableFailureCount": 25,
@@ -3966,22 +3966,21 @@
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 13,
"consecutiveFailures": 13,
"attributableFailureCount": 12,
"consecutiveFailures": 12,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 13,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 12,
"tokenizer_compatibility": 1
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 12
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T20:05:01.109364+00:00",
"lastTerminalAt": "2026-09-09T22:49:15.213951+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -3990,7 +3989,7 @@
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 7
"unresolvedFailureCount": 8
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 8,
@@ -4433,18 +4432,18 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 13,
"consecutiveFailures": 13,
"attributableFailureCount": 11,
"consecutiveFailures": 11,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 13,
"decisionTotal": 11,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 12
"tokenizer_compatibility": 10
},
"failureCount": 14,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-08T18:27:21+00:00",
@@ -4456,7 +4455,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 14,
"total": 12,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -6679,15 +6678,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1454,
"totalRecords": 1538,
"terminalRecords": 1456,
"totalRecords": 1540,
"totals": {
"attributableFailureCount": 388,
"decisionFailureRate": 0.8899,
"decisionSuccessRate": 0.1101,
"decisionTotal": 436,
"failureBreakdown": {
"ambiguous_runtime": 249,
"ambiguous_runtime": 251,
"backend_operator": 23,
"framework_architecture_unsupported": 266,
"memory_capacity": 11,
@@ -6699,21 +6698,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1406,
"failureCount": 1408,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 48,
"successRate": 0.033,
"total": 1454,
"unresolvedFailureCount": 1016
"total": 1456,
"unresolvedFailureCount": 1018
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 Iluvatar_mrv-100 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 Iluvatar_bi-150 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 Vastai_va16 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。",
@@ -6721,7 +6720,7 @@
"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 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。",
"GPU Sunrise_pt-200-x1 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-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 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -6742,6 +6741,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1538,
"summarizedRecords": 1540,
"version": 1
}