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

state: generation 5329 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 19:40:09 +00:00
parent 80645fdcd7
commit f90b54cbed
9 changed files with 2046 additions and 2071 deletions
Download Patch File Download Diff File Expand all files Collapse all files

139
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T19:27:43.149913+00:00",
"lastSyncTime": "2026-09-10T19:27:42.923434+00:00",
"generatedAt": "2026-09-10T19:38:05.803026+00:00",
"lastSyncTime": "2026-09-10T19:38:05.602511+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1791,30 +1791,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 75,
"decisionFailureRate": 0.8824,
"decisionSuccessRate": 0.1176,
"decisionTotal": 85,
"attributableFailureCount": 76,
"decisionFailureRate": 0.8837,
"decisionSuccessRate": 0.1163,
"decisionTotal": 86,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 47,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 27,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 142,
"failureRate": 0.9342,
"failureCount": 143,
"failureRate": 0.9346,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0658,
"successRate": 0.0654,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 152,
"total": 153,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2292,14 +2292,14 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 129,
"decisionFailureRate": 0.7288,
"decisionSuccessRate": 0.2712,
"decisionTotal": 177,
"attributableFailureCount": 130,
"decisionFailureRate": 0.7303,
"decisionSuccessRate": 0.2697,
"decisionTotal": 178,
"failureBreakdown": {
"ambiguous_runtime": 123,
"backend_operator": 4,
"framework_architecture_unsupported": 88,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
"model_load": 29,
"platform_infrastructure": 1,
@@ -2307,14 +2307,14 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 982,
"failureCount": 983,
"failureRate": 0.9534,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0466,
"total": 1030,
"total": 1031,
"unresolvedFailureCount": 852
},
"vllm": {
@@ -2445,7 +2445,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T19:27:43.145530+00:00",
"generatedAt": "2026-09-10T19:38:05.798763+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2608,27 +2608,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 75,
"decisionFailureRate": 0.8824,
"decisionSuccessRate": 0.1176,
"decisionTotal": 85,
"attributableFailureCount": 76,
"decisionFailureRate": 0.8837,
"decisionSuccessRate": 0.1163,
"decisionTotal": 86,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 47,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 27,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 142,
"failureRate": 0.9342,
"failureCount": 143,
"failureRate": 0.9346,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0658,
"total": 152,
"successRate": 0.0654,
"total": 153,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800": {
@@ -4172,11 +4172,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 4,
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 3,
"参数/模板问题": 1
},
"failureCount": 8,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4188,8 +4188,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 5
"total": 7,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -4270,27 +4270,27 @@
"unresolvedFailureCount": 3
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 16,
"consecutiveFailures": 8,
"attributableFailureCount": 17,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8421,
"decisionSuccessRate": 0.1579,
"decisionFailureRate": 0.8947,
"decisionSuccessRate": 0.1053,
"decisionTotal": 19,
"failureBreakdown": {
"framework_architecture_unsupported": 7,
"framework_architecture_unsupported": 8,
"model_load": 9,
"platform_infrastructure": 1
},
"failureCount": 17,
"failureRate": 0.85,
"failureCount": 18,
"failureRate": 0.9,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-10T19:27:42.923434+00:00",
"lastTerminalAt": "2026-09-10T19:38:05.602511+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.15,
"successCount": 2,
"successRate": 0.1,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 20,
@@ -4683,31 +4683,6 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|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-mlu",
"lastTerminalAt": "2026-09-08T16:13:44.313839+00:00",
"modelType": "starcoder2",
"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|text-generation|qwen3_5_moe|eschamoe": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -7047,17 +7022,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1626,
"totalRecords": 1713,
"terminalRecords": 1627,
"totalRecords": 1714,
"totals": {
"attributableFailureCount": 424,
"decisionFailureRate": 0.8908,
"decisionSuccessRate": 0.1092,
"decisionTotal": 476,
"attributableFailureCount": 425,
"decisionFailureRate": 0.891,
"decisionSuccessRate": 0.109,
"decisionTotal": 477,
"failureBreakdown": {
"ambiguous_runtime": 375,
"backend_operator": 40,
"framework_architecture_unsupported": 272,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
"model_load": 51,
"platform_infrastructure": 4,
@@ -7067,31 +7042,30 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1574,
"failureCount": 1575,
"failureRate": 0.968,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 52,
"successRate": 0.032,
"total": 1626,
"total": 1627,
"unresolvedFailureCount": 1146
},
"warnings": [
"GPU Ascend_910-b3 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 Iluvatar_mrv-100 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 MetaX_c-500 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 Iluvatar_bi-150 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 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 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。",
"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-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 Mthreads_s4000|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-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 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。",
@@ -7106,10 +7080,11 @@
"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 Iluvatar_bi-150|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。",
"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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1713,
"summarizedRecords": 1714,
"version": 1
}