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

state: generation 6004 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-12 03:34:42 +00:00
parent 01c85aae1e
commit 4ca13f4232
9 changed files with 2054 additions and 2051 deletions
Download Patch File Download Diff File Expand all files Collapse all files

95
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T03:14:58.686149+00:00",
"lastSyncTime": "2026-09-12T03:14:58.435392+00:00",
"generatedAt": "2026-09-12T03:32:36.014119+00:00",
"lastSyncTime": "2026-09-12T03:32:35.805010+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1800,18 +1800,19 @@
"unresolvedFailureCount": 4
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 18,
"attributableFailureCount": 19,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 18,
"decisionTotal": 19,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 2,
"framework_architecture_unsupported": 9,
"model_load": 5,
"repository_structure": 1,
"runtime_memory": 2
},
"failureCount": 25,
"failureCount": 26,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1821,7 +1822,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 25,
"total": 26,
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
@@ -2376,10 +2377,10 @@
"unresolvedFailureCount": 862
},
"vllm": {
"attributableFailureCount": 250,
"decisionFailureRate": 0.9881,
"decisionSuccessRate": 0.0119,
"decisionTotal": 253,
"attributableFailureCount": 251,
"decisionFailureRate": 0.9882,
"decisionSuccessRate": 0.0118,
"decisionTotal": 254,
"failureBreakdown": {
"ambiguous_runtime": 195,
"backend_operator": 33,
@@ -2387,19 +2388,19 @@
"memory_capacity": 6,
"model_load": 21,
"platform_infrastructure": 1,
"repository_structure": 5,
"repository_structure": 6,
"runtime_memory": 6,
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 470,
"failureCount": 471,
"failureRate": 0.9937,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0063,
"total": 473,
"total": 474,
"unresolvedFailureCount": 219
},
"vllm-mlu": {
@@ -2504,7 +2505,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T03:14:58.681095+00:00",
"generatedAt": "2026-09-12T03:32:36.009482+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2643,27 +2644,28 @@
"unresolvedFailureCount": 27
},
"Iluvatar_bi-150": {
"attributableFailureCount": 23,
"decisionFailureRate": 0.7419,
"decisionSuccessRate": 0.2581,
"decisionTotal": 31,
"attributableFailureCount": 24,
"decisionFailureRate": 0.75,
"decisionSuccessRate": 0.25,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 12,
"backend_operator": 5,
"framework_architecture_unsupported": 10,
"model_load": 6,
"repository_structure": 1,
"runtime_memory": 2,
"参数/模板问题": 2,
"验证失败": 30
},
"failureCount": 67,
"failureRate": 0.8933,
"failureCount": 68,
"failureRate": 0.8947,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.1067,
"total": 75,
"successRate": 0.1053,
"total": 76,
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
@@ -4413,23 +4415,24 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 2,
"backend_operator": 1,
"framework_architecture_unsupported": 2,
"model_load": 2
"model_load": 2,
"repository_structure": 1
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T03:05:47.937930+00:00",
"lastTerminalAt": "2026-09-12T03:32:35.805010+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4437,7 +4440,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 7,
"total": 8,
"unresolvedFailureCount": 2
},
"Iluvatar_mrv-100|unknown|text-generation": {
@@ -4619,18 +4622,18 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 15,
"attributableFailureCount": 14,
"consecutiveFailures": 14,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 15,
"decisionTotal": 14,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 2,
"tokenizer_compatibility": 13
"tokenizer_compatibility": 12
},
"failureCount": 17,
"failureCount": 16,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
@@ -4642,7 +4645,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 17,
"total": 16,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -7237,13 +7240,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1683,
"totalRecords": 1770,
"terminalRecords": 1684,
"totalRecords": 1771,
"totals": {
"attributableFailureCount": 455,
"decisionFailureRate": 0.8904,
"decisionSuccessRate": 0.1096,
"decisionTotal": 511,
"attributableFailureCount": 456,
"decisionFailureRate": 0.8906,
"decisionSuccessRate": 0.1094,
"decisionTotal": 512,
"failureBreakdown": {
"ambiguous_runtime": 394,
"backend_operator": 41,
@@ -7251,26 +7254,27 @@
"memory_capacity": 11,
"model_load": 65,
"platform_infrastructure": 4,
"repository_structure": 5,
"repository_structure": 6,
"runtime_memory": 6,
"tokenizer_compatibility": 47,
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1627,
"failureCount": 1628,
"failureRate": 0.9667,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.0333,
"total": 1683,
"total": 1684,
"unresolvedFailureCount": 1168
},
"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。",
@@ -7279,7 +7283,6 @@
"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。",
@@ -7301,6 +7304,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1770,
"summarizedRecords": 1771,
"version": 1
}