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

state: generation 5113 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 10:14:43 +00:00
parent 4385a2527f
commit ed2bdfe329
9 changed files with 2257 additions and 2258 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": "2026-09-10T09:47:33.599443+00:00",
"lastSyncTime": "2026-09-10T09:47:33.262404+00:00",
"generatedAt": "2026-09-10T10:12:25.956598+00:00",
"lastSyncTime": "2026-09-10T10:12:25.704447+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2147,12 +2147,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 51,
"ambiguous_runtime": 52,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 95,
"failureCount": 96,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2162,8 +2162,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 95,
"unresolvedFailureCount": 51
"total": 96,
"unresolvedFailureCount": 52
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2325,7 +2325,7 @@
"decisionSuccessRate": 0.0042,
"decisionTotal": 236,
"failureBreakdown": {
"ambiguous_runtime": 157,
"ambiguous_runtime": 158,
"backend_operator": 29,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2336,15 +2336,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 414,
"failureCount": 415,
"failureRate": 0.9976,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0024,
"total": 415,
"unresolvedFailureCount": 178
"total": 416,
"unresolvedFailureCount": 179
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T09:47:33.595423+00:00",
"generatedAt": "2026-09-10T10:12:25.950299+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2731,22 +2731,22 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 52,
"ambiguous_runtime": 53,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 242,
"failureRate": 0.949,
"failureCount": 243,
"failureRate": 0.9492,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.051,
"total": 255,
"unresolvedFailureCount": 195
"successRate": 0.0508,
"total": 256,
"unresolvedFailureCount": 196
},
"hygon_k100-ai": {
"attributableFailureCount": 38,
@@ -4504,18 +4504,18 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"decisionTotal": 8,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 8
"tokenizer_compatibility": 7
},
"failureCount": 10,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-08T18:27:21+00:00",
@@ -4527,7 +4527,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 10,
"total": 9,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -4605,21 +4605,20 @@
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 1
"ambiguous_runtime": 20
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T09:47:33.262382+00:00",
"lastTerminalAt": "2026-09-10T10:12:25.704447+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4628,7 +4627,7 @@
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 19
"unresolvedFailureCount": 20
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -7056,15 +7055,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1553,
"totalRecords": 1640,
"terminalRecords": 1554,
"totalRecords": 1641,
"totals": {
"attributableFailureCount": 405,
"decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118,
"decisionTotal": 456,
"failureBreakdown": {
"ambiguous_runtime": 327,
"ambiguous_runtime": 328,
"backend_operator": 34,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -7076,21 +7075,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1502,
"failureCount": 1503,
"failureRate": 0.9672,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 51,
"successRate": 0.0328,
"total": 1553,
"unresolvedFailureCount": 1095
"total": 1554,
"unresolvedFailureCount": 1096
},
"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。",
@@ -7098,7 +7097,7 @@
"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。",
@@ -7119,6 +7118,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1640,
"summarizedRecords": 1641,
"version": 1
}