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

state: generation 6643 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-13 09:42:21 +00:00
parent ba0a8c956b
commit 873b76ca87
9 changed files with 2184 additions and 2182 deletions
Download Patch File Download Diff File Expand all files Collapse all files

96
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-13T08:31:13.164252+00:00",
"lastSyncTime": "2026-09-13T08:31:12.943798+00:00",
"generatedAt": "2026-09-13T09:40:23.888574+00:00",
"lastSyncTime": "2026-09-13T09:40:23.641563+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1327,17 +1327,19 @@
"architectures": [
"spark2_5forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-12T10:55:22+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-13T09:33:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-12T10:55:22+00:00",
"latestFailureAt": "2026-09-13T09:33:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"XHToken/Spark-X2.5-1.7B",
"XHToken/Spark-X2.5-4B"
],
"sourceTaskIds": [
"4557415",
"4554931"
],
"targetGpu": "Vastai_va16",
@@ -2328,17 +2330,17 @@
"unresolvedFailureCount": 2
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 48,
"attributableFailureCount": 49,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 48,
"decisionTotal": 49,
"failureBreakdown": {
"ambiguous_runtime": 61,
"framework_architecture_unsupported": 42,
"framework_architecture_unsupported": 43,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 109,
"failureCount": 110,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2348,7 +2350,7 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 109,
"total": 110,
"unresolvedFailureCount": 61
},
"hygon_k100-ai|llamacpp|text-generation": {
@@ -2508,14 +2510,14 @@
"unresolvedFailureCount": 875
},
"vllm": {
"attributableFailureCount": 295,
"decisionFailureRate": 0.9899,
"decisionSuccessRate": 0.0101,
"decisionTotal": 298,
"attributableFailureCount": 296,
"decisionFailureRate": 0.99,
"decisionSuccessRate": 0.01,
"decisionTotal": 299,
"failureBreakdown": {
"ambiguous_runtime": 201,
"backend_operator": 34,
"framework_architecture_unsupported": 208,
"framework_architecture_unsupported": 209,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2524,14 +2526,14 @@
"tokenizer_compatibility": 7,
"参数/模板问题": 24
},
"failureCount": 521,
"failureCount": 522,
"failureRate": 0.9943,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0057,
"total": 524,
"total": 525,
"unresolvedFailureCount": 225
},
"vllm-mlu": {
@@ -2636,7 +2638,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T08:31:13.160082+00:00",
"generatedAt": "2026-09-13T09:40:23.884789+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 31,
@@ -2920,26 +2922,26 @@
"unresolvedFailureCount": 43
},
"Vastai_va16": {
"attributableFailureCount": 51,
"decisionFailureRate": 0.7969,
"decisionSuccessRate": 0.2031,
"decisionTotal": 64,
"attributableFailureCount": 52,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 65,
"failureBreakdown": {
"ambiguous_runtime": 63,
"framework_architecture_unsupported": 44,
"framework_architecture_unsupported": 45,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 257,
"failureRate": 0.9519,
"failureCount": 258,
"failureRate": 0.952,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0481,
"total": 270,
"successRate": 0.048,
"total": 271,
"unresolvedFailureCount": 206
},
"hygon_k100-ai": {
@@ -5000,21 +5002,21 @@
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 4
"ambiguous_runtime": 15,
"framework_architecture_unsupported": 5
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T08:31:12.943798+00:00",
"lastTerminalAt": "2026-09-13T09:40:23.641563+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -5023,7 +5025,7 @@
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 16
"unresolvedFailureCount": 15
},
"hygon_k100-ai|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -7481,17 +7483,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1769,
"totalRecords": 1856,
"terminalRecords": 1770,
"totalRecords": 1857,
"totals": {
"attributableFailureCount": 515,
"decisionFailureRate": 0.8972,
"decisionSuccessRate": 0.1028,
"decisionTotal": 574,
"attributableFailureCount": 516,
"decisionFailureRate": 0.8974,
"decisionSuccessRate": 0.1026,
"decisionTotal": 575,
"failureBreakdown": {
"ambiguous_runtime": 415,
"backend_operator": 43,
"framework_architecture_unsupported": 324,
"framework_architecture_unsupported": 325,
"memory_capacity": 11,
"model_load": 73,
"platform_infrastructure": 4,
@@ -7501,20 +7503,21 @@
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1710,
"failureRate": 0.9666,
"failureCount": 1711,
"failureRate": 0.9667,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 59,
"successRate": 0.0334,
"total": 1769,
"successRate": 0.0333,
"total": 1770,
"unresolvedFailureCount": 1191
},
"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。",
@@ -7523,7 +7526,6 @@
"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。",
@@ -7546,6 +7548,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1856,
"summarizedRecords": 1857,
"version": 1
}