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

state: generation 22018 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-08 01:14:18 +00:00
parent 668629334c
commit 6696c8b709
10 changed files with 2666 additions and 2686 deletions
Download Patch File Download Diff File Expand all files Collapse all files

248
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-08T00:13:15.008206+00:00",
"lastSyncTime": "2026-10-08T00:13:14.756688+00:00",
"generatedAt": "2026-10-08T01:09:06.324468+00:00",
"lastSyncTime": "2026-10-08T01:09:06.056781+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1379,17 +1379,19 @@
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-21T22:14:33.594032+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-22T00:42:42.844085+00:00",
"framework": "vllm-patch-tokenizer",
"latestFailureAt": "2026-09-21T22:14:33.594032+00:00",
"latestFailureAt": "2026-09-22T00:42:42.844085+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "mini_k3",
"sourceModelIds": [
"nkkbr/Mini-K3-1H-attnres-standard-v1_B",
"nkkbr/Mini-K3-1H-attnres-block6-v1_C"
],
"sourceTaskIds": [
"5009809",
"5008009"
],
"targetGpu": "hygon_k100-ai",
@@ -1758,7 +1760,7 @@
"iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3",
"architectures": [],
"evidenceCount": 3,
"evidenceCount": 4,
"expiresAt": "2026-10-22T02:44:31.355275+00:00",
"framework": "vllm_0_17_0_corex_4_4_0",
"latestFailureAt": "2026-09-22T02:44:31.355275+00:00",
@@ -1767,11 +1769,13 @@
"modelType": "mini_k3",
"sourceModelIds": [
"nkkbr/Mini-K3-1H-decay-g1-v2_B",
"nkkbr/Mini-K3-1H-attnres-block2-v1_B",
"nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C",
"nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B"
],
"sourceTaskIds": [
"5011150",
"5011149",
"5009715",
"5009624"
],
@@ -4158,30 +4162,30 @@
"unresolvedFailureCount": 82
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 51,
"decisionFailureRate": 0.7286,
"decisionSuccessRate": 0.2714,
"decisionTotal": 70,
"attributableFailureCount": 52,
"decisionFailureRate": 0.7324,
"decisionSuccessRate": 0.2676,
"decisionTotal": 71,
"failureBreakdown": {
"ambiguous_runtime": 32,
"backend_operator": 6,
"framework_architecture_unsupported": 26,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 8,
"runtime_memory": 10,
"参数/模板问题": 2
},
"failureCount": 85,
"failureRate": 0.8173,
"failureCount": 86,
"failureRate": 0.819,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.1827,
"successRate": 0.181,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 104,
"total": 105,
"unresolvedFailureCount": 34
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
@@ -5433,19 +5437,19 @@
"unresolvedFailureCount": 72
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 66,
"attributableFailureCount": 67,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 66,
"decisionTotal": 67,
"failureBreakdown": {
"ambiguous_runtime": 49,
"framework_architecture_unsupported": 27,
"framework_architecture_unsupported": 28,
"model_load": 15,
"repository_structure": 5,
"runtime_memory": 19,
"参数/模板问题": 24
},
"failureCount": 139,
"failureCount": 140,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"pendingCount": 0,
@@ -5455,7 +5459,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 139,
"total": 140,
"unresolvedFailureCount": 73
},
"hygon_k100-ai|vllm|text-generation": {
@@ -5689,50 +5693,50 @@
"unresolvedFailureCount": 110
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 66,
"attributableFailureCount": 67,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 66,
"decisionTotal": 67,
"failureBreakdown": {
"ambiguous_runtime": 49,
"framework_architecture_unsupported": 27,
"framework_architecture_unsupported": 28,
"model_load": 15,
"repository_structure": 5,
"runtime_memory": 19,
"参数/模板问题": 24
},
"failureCount": 139,
"failureCount": 140,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 139,
"total": 140,
"unresolvedFailureCount": 73
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 51,
"decisionFailureRate": 0.7286,
"decisionSuccessRate": 0.2714,
"decisionTotal": 70,
"attributableFailureCount": 52,
"decisionFailureRate": 0.7324,
"decisionSuccessRate": 0.2676,
"decisionTotal": 71,
"failureBreakdown": {
"ambiguous_runtime": 32,
"backend_operator": 6,
"framework_architecture_unsupported": 26,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 8,
"runtime_memory": 10,
"参数/模板问题": 2
},
"failureCount": 85,
"failureRate": 0.8173,
"failureCount": 86,
"failureRate": 0.819,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.1827,
"total": 104,
"successRate": 0.181,
"total": 105,
"unresolvedFailureCount": 34
},
"vllm_fix_tokenizer": {
@@ -5789,7 +5793,7 @@
"unresolvedFailureCount": 257
}
},
"generatedAt": "2026-10-08T00:13:14.993845+00:00",
"generatedAt": "2026-10-08T01:09:06.309813+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 121,
@@ -5954,16 +5958,16 @@
"unresolvedFailureCount": 571
},
"Iluvatar_bi-150": {
"attributableFailureCount": 768,
"decisionFailureRate": 0.8366,
"decisionSuccessRate": 0.1634,
"decisionTotal": 918,
"attributableFailureCount": 769,
"decisionFailureRate": 0.8368,
"decisionSuccessRate": 0.1632,
"decisionTotal": 919,
"failureBreakdown": {
"ambiguous_runtime": 665,
"architecture_compatibility": 15,
"backend_operator": 12,
"context_length": 29,
"framework_architecture_unsupported": 259,
"framework_architecture_unsupported": 260,
"memory_capacity": 153,
"model_load": 128,
"platform_infrastructure": 21,
@@ -5974,14 +5978,14 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1960,
"failureCount": 1961,
"failureRate": 0.9289,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 150,
"successRate": 0.0711,
"total": 2110,
"total": 2111,
"unresolvedFailureCount": 1171
},
"Iluvatar_mrv-100": {
@@ -6182,16 +6186,16 @@
"unresolvedFailureCount": 1322
},
"hygon_k100-ai": {
"attributableFailureCount": 746,
"attributableFailureCount": 747,
"decisionFailureRate": 0.954,
"decisionSuccessRate": 0.046,
"decisionTotal": 782,
"decisionTotal": 783,
"failureBreakdown": {
"ambiguous_runtime": 347,
"architecture_compatibility": 32,
"attention_backend": 1,
"context_length": 46,
"framework_architecture_unsupported": 259,
"framework_architecture_unsupported": 260,
"memory_capacity": 59,
"model_load": 75,
"platform_infrastructure": 4,
@@ -6202,14 +6206,14 @@
"日志缺失": 66,
"验证失败": 27
},
"failureCount": 1595,
"failureCount": 1596,
"failureRate": 0.9779,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 36,
"successRate": 0.0221,
"total": 1631,
"total": 1632,
"unresolvedFailureCount": 845
}
},
@@ -15829,14 +15833,14 @@
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mini_k3|none": {
"attributableFailureCount": 3,
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 3
"framework_architecture_unsupported": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "mini_k3",
@@ -15848,7 +15852,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mistral3|none": {
@@ -24545,14 +24549,14 @@
"unresolvedFailureCount": 6
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|mini_k3|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "mini_k3",
@@ -24564,7 +24568,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|mistral3|none": {
@@ -25809,10 +25813,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 14,
"参数/模板问题": 1
},
"failureCount": 16,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastPlatformFailureAt": null,
@@ -25824,8 +25828,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 16
"total": 15,
"unresolvedFailureCount": 15
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 4,
@@ -25881,16 +25885,16 @@
"unresolvedFailureCount": 11
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 3
"framework_architecture_unsupported": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"lastPlatformFailureAt": null,
@@ -25902,7 +25906,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
@@ -26307,9 +26311,8 @@
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 4,
"model_load": 1,
"repository_structure": 1,
"参数/模板问题": 13
},
"failureCount": 20,
@@ -27180,31 +27183,6 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma2|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-customized",
"lastTerminalAt": "2026-09-22T08:17:47.558862+00:00",
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"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|lfm2|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -27756,15 +27734,15 @@
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mini_k3|none": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 3
"framework_architecture_unsupported": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"lastTerminalAt": "2026-10-07T23:17:42.455387+00:00",
@@ -27777,7 +27755,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": {
@@ -29382,18 +29360,18 @@
"unresolvedFailureCount": 2
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|mini_k3|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastTerminalAt": "2026-10-07T20:23:14.668330+00:00",
"lastTerminalAt": "2026-10-08T01:09:06.056781+00:00",
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -29403,7 +29381,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|phi3small|compressed-tensors": {
@@ -29482,15 +29460,15 @@
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 2
"runtime_memory": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastTerminalAt": "2026-09-23T23:59:25.752490+00:00",
@@ -29503,7 +29481,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation|qwen3_vl|none": {
@@ -44340,14 +44318,14 @@
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mini_k3|none|30": {
"attributableFailureCount": 3,
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 3
"framework_architecture_unsupported": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 30,
@@ -44360,7 +44338,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mistral3|none|34": {
@@ -57658,14 +57636,14 @@
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|mini_k3|none|30": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 30,
@@ -57678,7 +57656,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|mistral3|none|34": {
@@ -59001,20 +58979,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17440,
"totalRecords": 17822,
"terminalRecords": 17442,
"totalRecords": 17824,
"totals": {
"attributableFailureCount": 6264,
"decisionFailureRate": 0.8648,
"decisionSuccessRate": 0.1352,
"decisionTotal": 7243,
"attributableFailureCount": 6266,
"decisionFailureRate": 0.8649,
"decisionSuccessRate": 0.1351,
"decisionTotal": 7245,
"failureBreakdown": {
"ambiguous_runtime": 4581,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 130,
"context_length": 327,
"framework_architecture_unsupported": 2282,
"framework_architecture_unsupported": 2284,
"memory_capacity": 1206,
"model_load": 571,
"platform_infrastructure": 955,
@@ -59025,14 +59003,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16461,
"failureCount": 16463,
"failureRate": 0.9439,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 955,
"successCount": 979,
"successRate": 0.0561,
"total": 17440,
"total": 17442,
"unresolvedFailureCount": 9242
},
"warnings": [
@@ -59042,14 +59020,14 @@
"GPU hygon_k100-ai 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 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 Mthreads_s4000 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 Cambricon_mlu-370-x8 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 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 Iluvatar_bi-100 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_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"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 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 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -59095,6 +59073,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17822,
"summarizedRecords": 17824,
"version": 1
}