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

state: generation 10316 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 06:28:09 +00:00
parent 44bae75efc
commit 1395b7af86
10 changed files with 2020 additions and 1907 deletions
Download Patch File Download Diff File Expand all files Collapse all files

331
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T05:59:18.919080+00:00",
"lastSyncTime": "2026-09-20T05:59:18.862303+00:00",
"generatedAt": "2026-09-20T06:27:56.581211+00:00",
"lastSyncTime": "2026-09-20T06:27:54.872487+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -516,6 +516,27 @@
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation"
},
"biren_166m|vllm|text-generation|architectures:sophiaforcausallm": {
"architectureSignature": "architectures:sophiaforcausallm",
"architectures": [
"sophiaforcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-19T17:18:17.894388+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-19T17:18:17.894388+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"Arain119/Sophia"
],
"sourceTaskIds": [
"4960871"
],
"targetGpu": "Biren_166m",
"taskType": "text-generation"
},
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:nemotron_h": {
"architectureSignature": "model_type:nemotron_h",
"architectures": [],
@@ -1767,11 +1788,12 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 85,
"activeBlockCount": 86,
"byGpuFramework": {
"Ascend_910-b3|vllm": 11,
"Ascend_910-b3|vllm_tokenizer_patch": 1,
"Ascend_910-b4|vllm": 12,
"Biren_166m|vllm": 1,
"Cambricon_mlu-370-x8|vllm": 2,
"Cambricon_mlu-370-x8|vllm-mlu": 5,
"Iluvatar_bi-150|vllm": 4,
@@ -2124,15 +2146,15 @@
"unresolvedFailureCount": 1
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 136,
"decisionFailureRate": 0.9315,
"decisionSuccessRate": 0.0685,
"decisionTotal": 146,
"attributableFailureCount": 137,
"decisionFailureRate": 0.932,
"decisionSuccessRate": 0.068,
"decisionTotal": 147,
"failureBreakdown": {
"ambiguous_runtime": 130,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 85,
"framework_architecture_unsupported": 86,
"memory_capacity": 1,
"model_load": 11,
"platform_infrastructure": 2,
@@ -2143,7 +2165,7 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 570,
"failureCount": 571,
"failureRate": 0.9828,
"framework": "unknown",
"pendingCount": 0,
@@ -2153,7 +2175,7 @@
"successRate": 0.0172,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 580,
"total": 581,
"unresolvedFailureCount": 432
},
"Biren_166m|unknown|visual-multi-modal": {
@@ -2178,26 +2200,26 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 29,
"decisionFailureRate": 0.6744,
"decisionSuccessRate": 0.3256,
"decisionTotal": 43,
"attributableFailureCount": 31,
"decisionFailureRate": 0.6889,
"decisionSuccessRate": 0.3111,
"decisionTotal": 45,
"failureBreakdown": {
"framework_architecture_unsupported": 22,
"framework_architecture_unsupported": 24,
"model_load": 6,
"tokenizer_compatibility": 1
},
"failureCount": 29,
"failureRate": 0.6744,
"failureCount": 31,
"failureRate": 0.6889,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.3256,
"successRate": 0.3111,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 43,
"total": 45,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -3559,9 +3581,9 @@
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 65,
"decisionFailureRate": 0.8025,
"decisionSuccessRate": 0.1975,
"decisionTotal": 81,
"decisionFailureRate": 0.7927,
"decisionSuccessRate": 0.2073,
"decisionTotal": 82,
"failureBreakdown": {
"ambiguous_runtime": 58,
"backend_operator": 8,
@@ -3574,16 +3596,16 @@
"参数/模板问题": 12
},
"failureCount": 135,
"failureRate": 0.894,
"failureRate": 0.8882,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 16,
"successRate": 0.106,
"successCount": 17,
"successRate": 0.1118,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 151,
"total": 152,
"unresolvedFailureCount": 70
},
"Mthreads_s4000|vllm|visual-multi-modal": {
@@ -4171,16 +4193,16 @@
"unresolvedFailureCount": 35
},
"unknown": {
"attributableFailureCount": 1855,
"decisionFailureRate": 0.6974,
"decisionSuccessRate": 0.3026,
"decisionTotal": 2660,
"attributableFailureCount": 1856,
"decisionFailureRate": 0.6975,
"decisionSuccessRate": 0.3025,
"decisionTotal": 2661,
"failureBreakdown": {
"ambiguous_runtime": 1962,
"architecture_compatibility": 100,
"backend_operator": 5,
"context_length": 157,
"framework_architecture_unsupported": 627,
"framework_architecture_unsupported": 628,
"memory_capacity": 443,
"model_load": 99,
"platform_infrastructure": 42,
@@ -4191,28 +4213,28 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 8301,
"failureCount": 8302,
"failureRate": 0.9116,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 42,
"successCount": 805,
"successRate": 0.0884,
"total": 9106,
"total": 9107,
"unresolvedFailureCount": 6404
},
"vllm": {
"attributableFailureCount": 3459,
"decisionFailureRate": 0.9799,
"decisionSuccessRate": 0.0201,
"decisionTotal": 3530,
"attributableFailureCount": 3461,
"decisionFailureRate": 0.9796,
"decisionSuccessRate": 0.0204,
"decisionTotal": 3533,
"failureBreakdown": {
"ambiguous_runtime": 1426,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
"context_length": 161,
"framework_architecture_unsupported": 1250,
"framework_architecture_unsupported": 1252,
"memory_capacity": 718,
"model_load": 197,
"platform_infrastructure": 864,
@@ -4221,14 +4243,14 @@
"tokenizer_compatibility": 406,
"参数/模板问题": 40
},
"failureCount": 5789,
"failureRate": 0.9879,
"failureCount": 5791,
"failureRate": 0.9877,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 71,
"successRate": 0.0121,
"total": 5860,
"successCount": 72,
"successRate": 0.0123,
"total": 5863,
"unresolvedFailureCount": 1466
},
"vllm-mlu": {
@@ -4341,7 +4363,7 @@
"unresolvedFailureCount": 23
}
},
"generatedAt": "2026-09-20T05:59:18.912281+00:00",
"generatedAt": "2026-09-20T06:27:56.574090+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 72,
@@ -4397,15 +4419,15 @@
"unresolvedFailureCount": 587
},
"Biren_166m": {
"attributableFailureCount": 166,
"decisionFailureRate": 0.8737,
"decisionSuccessRate": 0.1263,
"decisionTotal": 190,
"attributableFailureCount": 169,
"decisionFailureRate": 0.8756,
"decisionSuccessRate": 0.1244,
"decisionTotal": 193,
"failureBreakdown": {
"ambiguous_runtime": 130,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 108,
"framework_architecture_unsupported": 111,
"memory_capacity": 1,
"model_load": 17,
"platform_infrastructure": 2,
@@ -4416,14 +4438,14 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 601,
"failureRate": 0.9616,
"failureCount": 604,
"failureRate": 0.9618,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 24,
"successRate": 0.0384,
"total": 625,
"successRate": 0.0382,
"total": 628,
"unresolvedFailureCount": 433
},
"Cambricon_mlu-370-x4": {
@@ -4636,9 +4658,9 @@
},
"Mthreads_s4000": {
"attributableFailureCount": 69,
"decisionFailureRate": 0.6571,
"decisionSuccessRate": 0.3429,
"decisionTotal": 105,
"decisionFailureRate": 0.6509,
"decisionSuccessRate": 0.3491,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 104,
"backend_operator": 8,
@@ -4653,13 +4675,13 @@
"验证失败": 26
},
"failureCount": 351,
"failureRate": 0.907,
"failureRate": 0.9046,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 36,
"successRate": 0.093,
"total": 387,
"successCount": 37,
"successRate": 0.0954,
"total": 388,
"unresolvedFailureCount": 282
},
"Sunrise_pt-200-x1": {
@@ -5526,14 +5548,14 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_moe|compressed-tensors": {
"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",
"modelType": "qwen3_5_moe",
@@ -5545,7 +5567,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_moe|none": {
@@ -5776,6 +5798,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -8561,23 +8606,23 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.5,
"failureRate": 0.3333,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 0.5,
"successCount": 2,
"successRate": 0.6667,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|mistral3|none": {
@@ -9724,15 +9769,15 @@
"unresolvedFailureCount": 8
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 12,
"consecutiveFailures": 8,
"attributableFailureCount": 13,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9231,
"decisionSuccessRate": 0.0769,
"decisionTotal": 13,
"decisionFailureRate": 0.9286,
"decisionSuccessRate": 0.0714,
"decisionTotal": 14,
"failureBreakdown": {
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 9,
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 10,
"model_load": 1,
"runtime_memory": 2,
"参数/模板问题": 1
@@ -9741,7 +9786,7 @@
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-17T11:44:39.929678+00:00",
"lastTerminalAt": "2026-09-20T06:27:54.872472+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -9750,7 +9795,32 @@
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 7
"unresolvedFailureCount": 6
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T06:27:54.872414+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 10,
@@ -9961,20 +10031,20 @@
"unresolvedFailureCount": 2
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"framework_architecture_unsupported": 1,
"model_load": 3,
"model_load": 2,
"repository_structure": 1
},
"failureCount": 7,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -9986,7 +10056,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 7,
"total": 6,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|unknown|text-generation": {
@@ -10330,6 +10400,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-20T06:27:54.872414+00:00",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -11504,14 +11599,14 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_moe|compressed-tensors|34": {
"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",
"loadSizeLog2Bucket": 34,
@@ -11524,7 +11619,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_moe|none|34": {
@@ -11907,6 +12002,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|sophia_hybrid|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 31,
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -16561,7 +16680,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -16572,11 +16691,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successCount": 2,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|mistral3|none|34": {
@@ -17945,20 +18064,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 15758,
"totalRecords": 15861,
"terminalRecords": 15762,
"totalRecords": 15865,
"totals": {
"attributableFailureCount": 5701,
"decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383,
"decisionTotal": 6616,
"attributableFailureCount": 5704,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6620,
"failureBreakdown": {
"ambiguous_runtime": 3718,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 101,
"context_length": 318,
"framework_architecture_unsupported": 1957,
"framework_architecture_unsupported": 1960,
"memory_capacity": 1181,
"model_load": 474,
"platform_infrastructure": 922,
@@ -17969,14 +18088,14 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 14843,
"failureCount": 14846,
"failureRate": 0.9419,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 915,
"successCount": 916,
"successRate": 0.0581,
"total": 15758,
"total": 15762,
"unresolvedFailureCount": 8220
},
"warnings": [
@@ -18020,13 +18139,13 @@
"组合 Ascend_910-b3|vllm_tokenizer_patch|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|visual-multi-modal 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。",
"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 Cambricon_mlu-370-x8|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 Iluvatar_mrv-100|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-b3|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 Ascend_910-b3|vllm|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": 15861,
"summarizedRecords": 15865,
"version": 1
}