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

state: generation 6250 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-12 15:10:29 +00:00
parent 3d7d305284
commit 038396a08c
10 changed files with 2293 additions and 2272 deletions
Download Patch File Download Diff File Expand all files Collapse all files

174
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T14:41:33.654436+00:00",
"lastSyncTime": "2026-09-12T14:41:33.434355+00:00",
"generatedAt": "2026-09-12T15:08:42.536162+00:00",
"lastSyncTime": "2026-09-12T15:08:42.332272+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1714,9 +1714,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7
"ambiguous_runtime": 8
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "transformers",
"pendingCount": 0,
@@ -1726,8 +1726,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 7
"total": 8,
"unresolvedFailureCount": 8
},
"Iluvatar_bi-100|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -1816,26 +1816,26 @@
"unresolvedFailureCount": 32
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 4,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 6,
"attributableFailureCount": 5,
"decisionFailureRate": 0.7143,
"decisionSuccessRate": 0.2857,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 4,
"backend_operator": 3,
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 8,
"failureRate": 0.8,
"failureCount": 9,
"failureRate": 0.8182,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.2,
"successRate": 0.1818,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 10,
"total": 11,
"unresolvedFailureCount": 4
},
"Iluvatar_bi-150|vllm|text-generation": {
@@ -2378,17 +2378,17 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7
"ambiguous_runtime": 8
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 7,
"unresolvedFailureCount": 7
"total": 8,
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 146,
@@ -2483,23 +2483,23 @@
"unresolvedFailureCount": 8
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 4,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 6,
"attributableFailureCount": 5,
"decisionFailureRate": 0.7143,
"decisionSuccessRate": 0.2857,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 4,
"backend_operator": 3,
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 8,
"failureRate": 0.8,
"failureCount": 9,
"failureRate": 0.8182,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.2,
"total": 10,
"successRate": 0.1818,
"total": 11,
"unresolvedFailureCount": 4
},
"vllm_fix_tokenizer": {
@@ -2545,7 +2545,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T14:41:33.648453+00:00",
"generatedAt": "2026-09-12T15:08:42.531573+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 28,
@@ -2670,42 +2670,42 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 9,
"验证失败": 20
},
"failureCount": 28,
"failureCount": 29,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 28,
"unresolvedFailureCount": 28
"total": 29,
"unresolvedFailureCount": 29
},
"Iluvatar_bi-150": {
"attributableFailureCount": 30,
"decisionFailureRate": 0.7895,
"decisionSuccessRate": 0.2105,
"decisionTotal": 38,
"attributableFailureCount": 31,
"decisionFailureRate": 0.7949,
"decisionSuccessRate": 0.2051,
"decisionTotal": 39,
"failureBreakdown": {
"ambiguous_runtime": 12,
"backend_operator": 6,
"framework_architecture_unsupported": 14,
"framework_architecture_unsupported": 15,
"model_load": 7,
"repository_structure": 1,
"runtime_memory": 2,
"参数/模板问题": 2,
"验证失败": 30
},
"failureCount": 74,
"failureRate": 0.9024,
"failureCount": 75,
"failureRate": 0.9036,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.0976,
"total": 82,
"successRate": 0.0964,
"total": 83,
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
@@ -3329,14 +3329,14 @@
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|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_0_17_0_corex_4_4_0",
"modelType": "rwkv7",
@@ -3348,7 +3348,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors": {
@@ -4436,13 +4436,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "transformers",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T05:51:39.310788+00:00",
"lastTerminalAt": "2026-09-12T15:08:42.332272+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4450,8 +4450,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-150|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4567,9 +4567,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 19
"ambiguous_runtime": 18
},
"failureCount": 19,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -4581,8 +4581,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 19,
"unresolvedFailureCount": 19
"total": 18,
"unresolvedFailureCount": 18
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 5,
@@ -4880,9 +4880,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 2
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-09T11:33:22.442275+00:00",
@@ -4895,8 +4895,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0,
@@ -5841,6 +5841,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 32,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -7256,17 +7280,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1723,
"totalRecords": 1810,
"terminalRecords": 1725,
"totalRecords": 1812,
"totals": {
"attributableFailureCount": 484,
"decisionFailureRate": 0.8946,
"decisionSuccessRate": 0.1054,
"decisionTotal": 541,
"attributableFailureCount": 485,
"decisionFailureRate": 0.8948,
"decisionSuccessRate": 0.1052,
"decisionTotal": 542,
"failureBreakdown": {
"ambiguous_runtime": 404,
"ambiguous_runtime": 405,
"backend_operator": 42,
"framework_architecture_unsupported": 297,
"framework_architecture_unsupported": 298,
"memory_capacity": 11,
"model_load": 72,
"platform_infrastructure": 4,
@@ -7276,20 +7300,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1666,
"failureRate": 0.9669,
"failureCount": 1668,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0331,
"total": 1723,
"unresolvedFailureCount": 1178
"successRate": 0.033,
"total": 1725,
"unresolvedFailureCount": 1179
},
"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。",
@@ -7298,7 +7323,6 @@
"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。",
@@ -7320,6 +7344,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1810,
"summarizedRecords": 1812,
"version": 1
}