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

state: generation 6470 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-13 02:13:58 +00:00
parent 7494692a23
commit b6e4f65ae7
9 changed files with 2134 additions and 2163 deletions
Download Patch File Download Diff File Expand all files Collapse all files

135
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-13T02:03:44.065901+00:00",
"lastSyncTime": "2026-09-13T02:03:43.839608+00:00",
"generatedAt": "2026-09-13T02:12:15.268761+00:00",
"lastSyncTime": "2026-09-13T02:12:14.114179+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -967,20 +967,18 @@
"mthreads_s4000|vllm|text-generation|model_type:nemotron_h": {
"architectureSignature": "model_type:nemotron_h",
"architectures": [],
"evidenceCount": 2,
"expiresAt": "2026-10-05T07:05:21+00:00",
"evidenceCount": 1,
"expiresAt": "2026-10-13T02:09:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-05T07:05:21+00:00",
"latestFailureAt": "2026-09-13T02:09:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "nemotron_h",
"sourceModelIds": [
"nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4",
"nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15"
"primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8"
],
"sourceTaskIds": [
"4196911",
"4332642"
"4543931"
],
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation"
@@ -989,17 +987,17 @@
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-06T21:29:22+00:00",
"expiresAt": "2026-10-13T02:05:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-06T21:29:22+00:00",
"latestFailureAt": "2026-09-13T02:05:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"ornith-ai/Ornith-1.5-9B"
"primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8"
],
"sourceTaskIds": [
"4590818"
"4543902"
],
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation"
@@ -2161,21 +2159,21 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 32,
"attributableFailureCount": 34,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"decisionTotal": 34,
"failureBreakdown": {
"ambiguous_runtime": 41,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"model_load": 2,
"repository_structure": 1,
"runtime_memory": 2,
"参数/模板问题": 3
},
"failureCount": 76,
"failureCount": 78,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2185,7 +2183,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 76,
"total": 78,
"unresolvedFailureCount": 44
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -2486,14 +2484,14 @@
"unresolvedFailureCount": 870
},
"vllm": {
"attributableFailureCount": 286,
"decisionFailureRate": 0.9896,
"decisionSuccessRate": 0.0104,
"decisionTotal": 289,
"attributableFailureCount": 288,
"decisionFailureRate": 0.9897,
"decisionSuccessRate": 0.0103,
"decisionTotal": 291,
"failureBreakdown": {
"ambiguous_runtime": 201,
"backend_operator": 34,
"framework_architecture_unsupported": 200,
"framework_architecture_unsupported": 202,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2502,14 +2500,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 512,
"failureCount": 514,
"failureRate": 0.9942,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0058,
"total": 515,
"total": 517,
"unresolvedFailureCount": 225
},
"vllm-mlu": {
@@ -2614,7 +2612,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T02:03:44.061319+00:00",
"generatedAt": "2026-09-13T02:12:15.263958+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 30,
@@ -2848,14 +2846,14 @@
"unresolvedFailureCount": 74
},
"Mthreads_s4000": {
"attributableFailureCount": 33,
"decisionFailureRate": 0.9429,
"decisionSuccessRate": 0.0571,
"decisionTotal": 35,
"attributableFailureCount": 35,
"decisionFailureRate": 0.9459,
"decisionSuccessRate": 0.0541,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 41,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 1,
@@ -2863,14 +2861,14 @@
"参数/模板问题": 10,
"验证失败": 26
},
"failureCount": 110,
"failureRate": 0.9821,
"failureCount": 112,
"failureRate": 0.9825,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0179,
"total": 112,
"successRate": 0.0175,
"total": 114,
"unresolvedFailureCount": 77
},
"Sunrise_pt-200-x1": {
@@ -4778,22 +4776,22 @@
"unresolvedFailureCount": 0
},
"Mthreads_s4000|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,
"backend_operator": 3,
"framework_architecture_unsupported": 1
"ambiguous_runtime": 15,
"backend_operator": 2,
"framework_architecture_unsupported": 3
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T22:39:21.821546+00:00",
"lastTerminalAt": "2026-09-13T02:12:14.114155+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4802,7 +4800,7 @@
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 16
"unresolvedFailureCount": 15
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -5038,31 +5036,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|zaya|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-10T22:32:18.404549+00:00",
"modelType": "zaya",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|minicpm|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -7341,17 +7314,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1748,
"totalRecords": 1835,
"terminalRecords": 1750,
"totalRecords": 1837,
"totals": {
"attributableFailureCount": 501,
"decisionFailureRate": 0.8962,
"decisionSuccessRate": 0.1038,
"decisionTotal": 559,
"attributableFailureCount": 503,
"decisionFailureRate": 0.8966,
"decisionSuccessRate": 0.1034,
"decisionTotal": 561,
"failureBreakdown": {
"ambiguous_runtime": 411,
"backend_operator": 42,
"framework_architecture_unsupported": 313,
"framework_architecture_unsupported": 315,
"memory_capacity": 11,
"model_load": 73,
"platform_infrastructure": 4,
@@ -7361,21 +7334,20 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1690,
"failureRate": 0.9668,
"failureCount": 1692,
"failureRate": 0.9669,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 58,
"successRate": 0.0332,
"total": 1748,
"successRate": 0.0331,
"total": 1750,
"unresolvedFailureCount": 1185
},
"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。",
@@ -7384,6 +7356,7 @@
"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。",
@@ -7406,6 +7379,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1835,
"summarizedRecords": 1837,
"version": 1
}