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

state: generation 18056 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-28 20:25:49 +00:00
parent d2e76863a1
commit 67aa39c8dd
8 changed files with 1677 additions and 1585 deletions
Download Patch File Download Diff File Expand all files Collapse all files

208
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-28T19:53:46.167869+00:00",
"lastSyncTime": "2026-09-28T19:53:45.860595+00:00",
"generatedAt": "2026-09-28T20:24:13.337116+00:00",
"lastSyncTime": "2026-09-28T20:24:13.064268+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -5324,15 +5324,15 @@
"unresolvedFailureCount": 158
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 74,
"decisionFailureRate": 0.7629,
"decisionSuccessRate": 0.2371,
"decisionTotal": 97,
"attributableFailureCount": 75,
"decisionFailureRate": 0.7653,
"decisionSuccessRate": 0.2347,
"decisionTotal": 98,
"failureBreakdown": {
"ambiguous_runtime": 75,
"attention_backend": 2,
"backend_operator": 8,
"framework_architecture_unsupported": 53,
"framework_architecture_unsupported": 54,
"memory_capacity": 1,
"model_load": 2,
"platform_infrastructure": 1,
@@ -5341,17 +5341,17 @@
"tokenizer_compatibility": 2,
"参数/模板问题": 12
},
"failureCount": 162,
"failureRate": 0.8757,
"failureCount": 163,
"failureRate": 0.8763,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 23,
"successRate": 0.1243,
"successRate": 0.1237,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 185,
"total": 186,
"unresolvedFailureCount": 87
},
"Mthreads_s4000|vllm|visual-multi-modal": {
@@ -5798,19 +5798,19 @@
"unresolvedFailureCount": 72
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 55,
"attributableFailureCount": 56,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 55,
"decisionTotal": 56,
"failureBreakdown": {
"ambiguous_runtime": 41,
"framework_architecture_unsupported": 20,
"framework_architecture_unsupported": 21,
"model_load": 11,
"repository_structure": 5,
"runtime_memory": 19,
"参数/模板问题": 11
},
"failureCount": 107,
"failureCount": 108,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"pendingCount": 0,
@@ -5820,7 +5820,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 107,
"total": 108,
"unresolvedFailureCount": 52
},
"hygon_k100-ai|vllm|text-generation": {
@@ -5976,17 +5976,17 @@
"unresolvedFailureCount": 6473
},
"vllm": {
"attributableFailureCount": 3626,
"decisionFailureRate": 0.9739,
"decisionSuccessRate": 0.0261,
"decisionTotal": 3723,
"attributableFailureCount": 3627,
"decisionFailureRate": 0.974,
"decisionSuccessRate": 0.026,
"decisionTotal": 3724,
"failureBreakdown": {
"ambiguous_runtime": 1586,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 93,
"context_length": 161,
"framework_architecture_unsupported": 1360,
"framework_architecture_unsupported": 1361,
"memory_capacity": 725,
"model_load": 220,
"platform_infrastructure": 871,
@@ -5995,14 +5995,14 @@
"tokenizer_compatibility": 416,
"参数/模板问题": 50
},
"failureCount": 6133,
"failureCount": 6134,
"failureRate": 0.9844,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 871,
"successCount": 97,
"successRate": 0.0156,
"total": 6230,
"total": 6231,
"unresolvedFailureCount": 1636
},
"vllm-customized": {
@@ -6053,26 +6053,26 @@
"unresolvedFailureCount": 96
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 55,
"attributableFailureCount": 56,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 55,
"decisionTotal": 56,
"failureBreakdown": {
"ambiguous_runtime": 41,
"framework_architecture_unsupported": 20,
"framework_architecture_unsupported": 21,
"model_load": 11,
"repository_structure": 5,
"runtime_memory": 19,
"参数/模板问题": 11
},
"failureCount": 107,
"failureCount": 108,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 107,
"total": 108,
"unresolvedFailureCount": 52
},
"vllm_0_17_0_corex_4_4_0": {
@@ -6153,7 +6153,7 @@
"unresolvedFailureCount": 197
}
},
"generatedAt": "2026-09-28T19:53:46.150389+00:00",
"generatedAt": "2026-09-28T20:24:13.323532+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6458,15 +6458,15 @@
"unresolvedFailureCount": 763
},
"Mthreads_s4000": {
"attributableFailureCount": 78,
"decisionFailureRate": 0.6393,
"decisionSuccessRate": 0.3607,
"decisionTotal": 122,
"attributableFailureCount": 79,
"decisionFailureRate": 0.6423,
"decisionSuccessRate": 0.3577,
"decisionTotal": 123,
"failureBreakdown": {
"ambiguous_runtime": 121,
"attention_backend": 2,
"backend_operator": 8,
"framework_architecture_unsupported": 54,
"framework_architecture_unsupported": 55,
"memory_capacity": 1,
"model_load": 5,
"platform_infrastructure": 1,
@@ -6477,14 +6477,14 @@
"日志缺失": 96,
"验证失败": 26
},
"failureCount": 378,
"failureRate": 0.8957,
"failureCount": 379,
"failureRate": 0.896,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 44,
"successRate": 0.1043,
"total": 422,
"successRate": 0.104,
"total": 423,
"unresolvedFailureCount": 299
},
"Sunrise_pt-200-x1": {
@@ -6545,16 +6545,16 @@
"unresolvedFailureCount": 1321
},
"hygon_k100-ai": {
"attributableFailureCount": 735,
"decisionFailureRate": 0.9533,
"decisionSuccessRate": 0.0467,
"decisionTotal": 771,
"attributableFailureCount": 736,
"decisionFailureRate": 0.9534,
"decisionSuccessRate": 0.0466,
"decisionTotal": 772,
"failureBreakdown": {
"ambiguous_runtime": 339,
"architecture_compatibility": 32,
"attention_backend": 1,
"context_length": 46,
"framework_architecture_unsupported": 252,
"framework_architecture_unsupported": 253,
"memory_capacity": 59,
"model_load": 71,
"platform_infrastructure": 4,
@@ -6565,14 +6565,14 @@
"日志缺失": 66,
"验证失败": 27
},
"failureCount": 1562,
"failureCount": 1563,
"failureRate": 0.9775,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 36,
"successRate": 0.0225,
"total": 1598,
"total": 1599,
"unresolvedFailureCount": 823
}
},
@@ -20655,6 +20655,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|spark2_5|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -22487,6 +22510,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -48392,6 +48438,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|spark2_5|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -51281,6 +51351,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -51880,20 +51974,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17081,
"totalRecords": 17302,
"terminalRecords": 17083,
"totalRecords": 17304,
"totals": {
"attributableFailureCount": 6124,
"attributableFailureCount": 6126,
"decisionFailureRate": 0.8638,
"decisionSuccessRate": 0.1362,
"decisionTotal": 7090,
"decisionTotal": 7092,
"failureBreakdown": {
"ambiguous_runtime": 4430,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 322,
"framework_architecture_unsupported": 2179,
"framework_architecture_unsupported": 2181,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 938,
@@ -51904,14 +51998,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16115,
"failureRate": 0.9434,
"failureCount": 16117,
"failureRate": 0.9435,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 938,
"successCount": 966,
"successRate": 0.0566,
"total": 17081,
"successRate": 0.0565,
"total": 17083,
"unresolvedFailureCount": 9053
},
"warnings": [
@@ -51941,6 +52035,7 @@
"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 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。",
"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 Kunlunxin_p-800|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 MetaX_c-500|vllm|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 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。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51965,11 +52060,10 @@
"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 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 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 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 Kunlunxin_p-800|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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17302,
"summarizedRecords": 17304,
"version": 1
}