state: generation 24429 (cycle)

This commit is contained in:
2026-10-13 22:18:17 +00:00
parent 384524b659
commit e6d29e9c63
8 changed files with 1720 additions and 1765 deletions

View File

@@ -2729,7 +2729,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-13T21:49:06.756758+00:00", "generatedAt": "2026-10-13T22:17:19.128893+00:00",
"summary": { "summary": {
"activeBlockCount": 136, "activeBlockCount": 136,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -443,7 +443,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-13T22:16:16.669034+00:00", "generatedAt": "2026-10-13T22:18:11.177524+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,

View File

@@ -1,5 +1,5 @@
{ {
"catalogUpdatedAt": "2026-10-13T22:16:16.669034+00:00", "catalogUpdatedAt": "2026-10-13T22:18:11.177524+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-10-13T22:16:16.669034+00:00", "generatedAt": "2026-10-13T22:18:11.177524+00:00",
"gpuCatalog": { "gpuCatalog": {
"Ascend_910-b3": { "Ascend_910-b3": {
"canVerify": true, "canVerify": true,
@@ -6371,6 +6371,6 @@
"updateTime": "2025-12-22 08:59:53" "updateTime": "2025-12-22 08:59:53"
} }
], ],
"taskTreeUpdatedAt": "2026-10-13T22:16:16.669034+00:00", "taskTreeUpdatedAt": "2026-10-13T22:18:11.177524+00:00",
"version": 1 "version": 1
} }

View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-13T17:14:10.024620+00:00", "generatedAt": "2026-10-13T22:17:19.035058+00:00",
"lastSyncTime": "2026-10-13T17:14:09.775028+00:00", "lastSyncTime": "2026-10-13T22:17:18.970469+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2551,25 +2551,6 @@
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation" "taskType": "text-generation"
}, },
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:mellum": {
"architectureSignature": "model_type:mellum",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-13T21:09:21+00:00",
"framework": "vllm_fix_tokenizer",
"latestFailureAt": "2026-09-13T21:09:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "mellum",
"sourceModelIds": [
"JetBrains/Mellum2-12B-A2.5B-Instruct"
],
"sourceTaskIds": [
"4152538"
],
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation"
},
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": { "sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5", "architectureSignature": "model_type:qwen3_5",
"architectures": [], "architectures": [],
@@ -2753,7 +2734,7 @@
} }
}, },
"architectureCompatibilitySummary": { "architectureCompatibilitySummary": {
"activeBlockCount": 137, "activeBlockCount": 136,
"byGpuFramework": { "byGpuFramework": {
"Ascend_910-b3|vllm": 8, "Ascend_910-b3|vllm": 8,
"Ascend_910-b3|vllm_tokenizer_patch": 10, "Ascend_910-b3|vllm_tokenizer_patch": 10,
@@ -2777,7 +2758,7 @@
"MetaX_c-500|vllm_tokenizer_patch": 4, "MetaX_c-500|vllm_tokenizer_patch": 4,
"Mthreads_s4000|vllm": 5, "Mthreads_s4000|vllm": 5,
"Sunrise_pt-200-x1|vllm": 2, "Sunrise_pt-200-x1|vllm": 2,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 3, "Sunrise_pt-200-x1|vllm_fix_tokenizer": 2,
"Vastai_va16|vllm": 4, "Vastai_va16|vllm": 4,
"Vastai_va16|vllm_fix_tokenizer": 2, "Vastai_va16|vllm_fix_tokenizer": 2,
"hygon_k100-ai|vllm": 6, "hygon_k100-ai|vllm": 6,
@@ -2884,20 +2865,20 @@
"framework_architecture_unsupported": 44, "framework_architecture_unsupported": 44,
"memory_capacity": 1, "memory_capacity": 1,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"参数/模板问题": 37 "参数/模板问题": 38
}, },
"failureCount": 187, "failureCount": 188,
"failureRate": 0.9791, "failureRate": 0.9792,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 4, "successCount": 4,
"successRate": 0.0209, "successRate": 0.0208,
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 191, "total": 192,
"unresolvedFailureCount": 132 "unresolvedFailureCount": 133
}, },
"Ascend_910-b3|vllm|text-generation": { "Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 75, "attributableFailureCount": 75,
@@ -4424,9 +4405,9 @@
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 188, "ambiguous_runtime": 188,
"参数/模板问题": 6 "参数/模板问题": 7
}, },
"failureCount": 194, "failureCount": 195,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -4436,8 +4417,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 194, "total": 195,
"unresolvedFailureCount": 194 "unresolvedFailureCount": 195
}, },
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 61, "attributableFailureCount": 61,
@@ -4622,9 +4603,9 @@
"ambiguous_runtime": 1, "ambiguous_runtime": 1,
"framework_architecture_unsupported": 6, "framework_architecture_unsupported": 6,
"model_load": 1, "model_load": 1,
"参数/模板问题": 37 "参数/模板问题": 38
}, },
"failureCount": 45, "failureCount": 46,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"pendingCount": 0, "pendingCount": 0,
@@ -4634,8 +4615,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 45, "total": 46,
"unresolvedFailureCount": 38 "unresolvedFailureCount": 39
}, },
"MetaX_c-500|vllm|feature_emb": { "MetaX_c-500|vllm|feature_emb": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -5312,9 +5293,9 @@
"model_load": 15, "model_load": 15,
"repository_structure": 5, "repository_structure": 5,
"runtime_memory": 19, "runtime_memory": 19,
"参数/模板问题": 54 "参数/模板问题": 55
}, },
"failureCount": 173, "failureCount": 174,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-patch-tokenizer", "framework": "vllm-patch-tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -5324,8 +5305,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 173, "total": 174,
"unresolvedFailureCount": 105 "unresolvedFailureCount": 106
}, },
"hygon_k100-ai|vllm|text-generation": { "hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 665, "attributableFailureCount": 665,
@@ -5568,17 +5549,17 @@
"model_load": 15, "model_load": 15,
"repository_structure": 5, "repository_structure": 5,
"runtime_memory": 19, "runtime_memory": 19,
"参数/模板问题": 54 "参数/模板问题": 55
}, },
"failureCount": 173, "failureCount": 174,
"failureRate": 1.0, "failureRate": 1.0,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"total": 173, "total": 174,
"unresolvedFailureCount": 105 "unresolvedFailureCount": 106
}, },
"vllm_0_17_0_corex_4_4_0": { "vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 55, "attributableFailureCount": 55,
@@ -5617,17 +5598,17 @@
"model_load": 13, "model_load": 13,
"platform_infrastructure": 31, "platform_infrastructure": 31,
"tokenizer_compatibility": 97, "tokenizer_compatibility": 97,
"参数/模板问题": 22 "参数/模板问题": 23
}, },
"failureCount": 656, "failureCount": 657,
"failureRate": 0.9924, "failureRate": 0.9924,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 31, "platformFailureCount": 31,
"successCount": 5, "successCount": 5,
"successRate": 0.0076, "successRate": 0.0076,
"total": 661, "total": 662,
"unresolvedFailureCount": 441 "unresolvedFailureCount": 442
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"attributableFailureCount": 170, "attributableFailureCount": 170,
@@ -5645,20 +5626,20 @@
"repository_structure": 3, "repository_structure": 3,
"runtime_memory": 3, "runtime_memory": 3,
"tokenizer_compatibility": 2, "tokenizer_compatibility": 2,
"参数/模板问题": 121 "参数/模板问题": 123
}, },
"failureCount": 507, "failureCount": 509,
"failureRate": 0.9807, "failureRate": 0.9807,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 3, "platformFailureCount": 3,
"successCount": 10, "successCount": 10,
"successRate": 0.0193, "successRate": 0.0193,
"total": 517, "total": 519,
"unresolvedFailureCount": 334 "unresolvedFailureCount": 336
} }
}, },
"generatedAt": "2026-10-13T17:14:10.012605+00:00", "generatedAt": "2026-10-13T22:17:19.022868+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 130, "attributableFailureCount": 130,
@@ -5673,19 +5654,19 @@
"platform_infrastructure": 1, "platform_infrastructure": 1,
"repository_structure": 1, "repository_structure": 1,
"tokenizer_compatibility": 3, "tokenizer_compatibility": 3,
"参数/模板问题": 69, "参数/模板问题": 70,
"日志缺失": 3, "日志缺失": 3,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 394, "failureCount": 395,
"failureRate": 0.9471, "failureRate": 0.9472,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 22, "successCount": 22,
"successRate": 0.0529, "successRate": 0.0528,
"total": 416, "total": 417,
"unresolvedFailureCount": 263 "unresolvedFailureCount": 264
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"attributableFailureCount": 337, "attributableFailureCount": 337,
@@ -5899,19 +5880,19 @@
"repository_structure": 2, "repository_structure": 2,
"runtime_memory": 3, "runtime_memory": 3,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 50, "参数/模板问题": 51,
"日志缺失": 1, "日志缺失": 1,
"验证失败": 23 "验证失败": 23
}, },
"failureCount": 451, "failureCount": 452,
"failureRate": 0.9847, "failureRate": 0.9847,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 7, "successCount": 7,
"successRate": 0.0153, "successRate": 0.0153,
"total": 458, "total": 459,
"unresolvedFailureCount": 351 "unresolvedFailureCount": 352
}, },
"Kunlunxin_r-200-8f": { "Kunlunxin_r-200-8f": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -5949,19 +5930,19 @@
"repository_structure": 114, "repository_structure": 114,
"runtime_memory": 2, "runtime_memory": 2,
"tokenizer_compatibility": 79, "tokenizer_compatibility": 79,
"参数/模板问题": 445, "参数/模板问题": 446,
"日志缺失": 15, "日志缺失": 15,
"验证失败": 48 "验证失败": 48
}, },
"failureCount": 1503, "failureCount": 1504,
"failureRate": 0.9109, "failureRate": 0.911,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 5, "platformFailureCount": 5,
"successCount": 147, "successCount": 147,
"successRate": 0.0891, "successRate": 0.089,
"total": 1650, "total": 1651,
"unresolvedFailureCount": 816 "unresolvedFailureCount": 817
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"attributableFailureCount": 91, "attributableFailureCount": 91,
@@ -6067,19 +6048,19 @@
"repository_structure": 121, "repository_structure": 121,
"runtime_memory": 74, "runtime_memory": 74,
"tokenizer_compatibility": 79, "tokenizer_compatibility": 79,
"参数/模板问题": 436, "参数/模板问题": 437,
"日志缺失": 66, "日志缺失": 66,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 1631, "failureCount": 1632,
"failureRate": 0.9784, "failureRate": 0.9784,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 4, "platformFailureCount": 4,
"successCount": 36, "successCount": 36,
"successRate": 0.0216, "successRate": 0.0216,
"total": 1667, "total": 1668,
"unresolvedFailureCount": 879 "unresolvedFailureCount": 880
} }
}, },
"observedGpuMemoryGiB": { "observedGpuMemoryGiB": {
@@ -26387,7 +26368,7 @@
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-10T13:04:00.870447+00:00", "lastTerminalAt": "2026-10-13T22:17:18.970462+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -26533,10 +26514,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 3, "ambiguous_runtime": 3
"参数/模板问题": 1
}, },
"failureCount": 4, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -26548,8 +26528,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 4, "total": 3,
"unresolvedFailureCount": 4 "unresolvedFailureCount": 3
}, },
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -26735,22 +26715,22 @@
"unresolvedFailureCount": 9 "unresolvedFailureCount": 9
}, },
"MetaX_c-500|vllm_tokenizer_patch|text-generation": { "MetaX_c-500|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 5, "attributableFailureCount": 4,
"consecutiveFailures": 5, "consecutiveFailures": 4,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 5, "decisionTotal": 4,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 4, "framework_architecture_unsupported": 3,
"model_load": 1, "model_load": 1,
"参数/模板问题": 15 "参数/模板问题": 16
}, },
"failureCount": 20, "failureCount": 20,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-10T15:45:17.258678+00:00", "lastTerminalAt": "2026-10-13T22:17:18.970469+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -26759,7 +26739,7 @@
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 20, "total": 20,
"unresolvedFailureCount": 15 "unresolvedFailureCount": 16
}, },
"Mthreads_s4000|unknown|text-generation": { "Mthreads_s4000|unknown|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -26906,7 +26886,7 @@
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-patch-tokenizer", "framework": "vllm-patch-tokenizer",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-10T11:17:52.552072+00:00", "lastTerminalAt": "2026-10-13T22:17:18.970452+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -27270,31 +27250,6 @@
"total": 2, "total": 2,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 2
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-10-08T05:42:37.051754+00:00",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|compressed-tensors": { "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|compressed-tensors": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"consecutiveFailures": 0, "consecutiveFailures": 0,
@@ -59354,8 +59309,8 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17861, "terminalRecords": 17865,
"totalRecords": 18390, "totalRecords": 18394,
"totals": { "totals": {
"attributableFailureCount": 6325, "attributableFailureCount": 6325,
"decisionFailureRate": 0.8655, "decisionFailureRate": 0.8655,
@@ -59374,35 +59329,35 @@
"repository_structure": 742, "repository_structure": 742,
"runtime_memory": 101, "runtime_memory": 101,
"tokenizer_compatibility": 696, "tokenizer_compatibility": 696,
"参数/模板问题": 3557, "参数/模板问题": 3561,
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16878, "failureCount": 16882,
"failureRate": 0.945, "failureRate": 0.945,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 964, "platformFailureCount": 964,
"successCount": 983, "successCount": 983,
"successRate": 0.055, "successRate": 0.055,
"total": 17861, "total": 17865,
"unresolvedFailureCount": 9589 "unresolvedFailureCount": 9593
}, },
"warnings": [ "warnings": [
"GPU hygon_k100-ai 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-x8 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 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 Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b3 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 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 Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。", "GPU Iluvatar_bi-100 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 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 Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高(≥50%),建议重点关注。", "GPU Kunlunxin_p-800 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 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 Iluvatar_mrv-100 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-x4 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 Ascend_910-b4 本地统计失败率偏高(≥50%),建议重点关注。",
"组合 Vastai_va16|vllm_fix_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 Vastai_va16|vllm_fix_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 Iluvatar_bi-150|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 Iluvatar_bi-150|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 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 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。",
@@ -59448,6 +59403,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 18390, "summarizedRecords": 18394,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,6 @@
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-13T22:17:18.970452+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T13:12:18.147765+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5513114", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-13T22:17:18.970462+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T12:52:58.552750+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5512698", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-13T22:17:18.970469+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T12:30:24.554632+00:00", "targetGpu": "MetaX_c-500", "taskId": "5512351", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-11T00:13:59.966347+00:00", "modelId": "Aratako/calm3-22b-RP-v0.1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-11T00:09:56+00:00", "targetGpu": "hygon_k100-ai", "taskId": "3993725", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-11T00:13:59.966347+00:00", "modelId": "Aratako/calm3-22b-RP-v0.1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-11T00:09:56+00:00", "targetGpu": "hygon_k100-ai", "taskId": "3993725", "taskType": "text-generation", "verifyResult": null}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-10-10T03:15:33.370676+00:00", "modelId": "unsloth/LFM2-2.6B-Exp-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-10T03:10:09+00:00", "targetGpu": "hygon_k100-ai", "taskId": "3872734", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-10-10T03:15:33.370676+00:00", "modelId": "unsloth/LFM2-2.6B-Exp-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-10T03:10:09+00:00", "targetGpu": "hygon_k100-ai", "taskId": "3872734", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-08T15:17:12.844319+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-08T15:05:20+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5007314", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-08T15:17:12.844319+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-08T15:05:20+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5007314", "taskType": "text-generation", "verifyResult": null}
@@ -295,6 +298,3 @@
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T13:04:00.870415+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:49.252673+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260100", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T13:04:00.870415+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:49.252673+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260100", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851172+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:49.244657+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260102", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851172+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:49.244657+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260102", "taskType": "text-generation", "verifyResult": null}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-10-10T23:28:05.253072+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409915, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409915}, "outcome": "failed", "status": "success", "submitTime": "2026-10-03T16:15:49.052393+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5260092", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-10-10T23:28:05.253072+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409915, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409915}, "outcome": "failed", "status": "success", "submitTime": "2026-10-03T16:15:49.052393+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5260092", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851099+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:48.964174+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260086", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851274+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:48.958081+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260088", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:42:37.051754+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20321390048, "estimatedRequiredGiB": 22.734, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20341996128, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20341996128}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:48.870520+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5260084", "taskType": "text-generation", "verifyResult": null}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "9a4e10bb2d8c4c8dad11bea544a5a02917a8034ee5f54cc443de4e6fbce58825", ".modelhub_state/architecture_compatibility_blacklist.json": "f684be139972fe7042407309dd68b8847ad629573c5e84dbd51c0eea8383c685",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "067de2016ded57ba59970529ac431f65f043652e410e02a7a5b59f10032569c4", ".modelhub_state/market_intelligence.json": "d319fff54b5e1d68c560159424d5d44b0c0902a4ede1e5743caf85859d1dcf66",
".modelhub_state/official_capabilities.json": "92bca3764167d1581f2ce80df8d31839cd48039edbe2322febbb8e15b465345a", ".modelhub_state/official_capabilities.json": "2bafb85ae022f5215c48152e2a7ba6cad802e6e289a5dce924d40b8dcd970785",
".modelhub_state/outcome_checkpoint.json": "72b99c109f4da34b218744b72491d71e7b9e2a4262d46131170a6be6b7bbc8ce", ".modelhub_state/outcome_checkpoint.json": "11bd6657f10c10dce8ce8d6d018569e42c523b9babca1d11689dfecd2c36af12",
".modelhub_state/queue_cleanup_latest.json": "a853c3ecd05b6eb13dc78028071c981c78c9adf73c9831a523b9562a8bdb1610", ".modelhub_state/queue_cleanup_latest.json": "a853c3ecd05b6eb13dc78028071c981c78c9adf73c9831a523b9562a8bdb1610",
".modelhub_state/recent_outcomes.jsonl": "d5f3321c7c835be11fc790c6b04936eee563f577da3818cfa5dc8aa7c8332239", ".modelhub_state/recent_outcomes.jsonl": "f140f32fe2dfebd3c84d5dae02f318bab3dc350b5d57daa1e908e7a53a9bc4f9",
".modelhub_state/recovery_active_tasks.jsonl": "89994ead1ece463e6089842710c3a0f43ebfb6759a3941339d063857bfc05d1e", ".modelhub_state/recovery_active_tasks.jsonl": "fa18646ec481355577ff69f32b086724121bc3871ca16c5643df8c6f0a81876b",
".modelhub_state/recovery_intents.jsonl": "336eb7566825629781cba130976f5c2b8d90ae85df13b97a860adb9ba002ff02", ".modelhub_state/recovery_intents.jsonl": "d9f4e3d6dcd0a2bb84cdc0b74e2613f13d71dd050ac5092a2ba72de980b41471",
".modelhub_state/routing_intelligence.json": "f920730c464e347d5b67191f75adb1f011bd44716de89e299cbdfae6a2b2d9c0", ".modelhub_state/routing_intelligence.json": "f920730c464e347d5b67191f75adb1f011bd44716de89e299cbdfae6a2b2d9c0",
".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b", ".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b",
".modelhub_state/worker_crashes.jsonl": "a6b56caed5c7afeb803f8701393cf4660f7e9799eb5ff84af826a142e16d9b00", ".modelhub_state/worker_crashes.jsonl": "a6b56caed5c7afeb803f8701393cf4660f7e9799eb5ff84af826a142e16d9b00",
"ledger/submissions.jsonl": "65f5568c3f9bb9032870e7be1c3c2bc2a179079508b57168264b340e908bceae", "ledger/submissions.jsonl": "65f5568c3f9bb9032870e7be1c3c2bc2a179079508b57168264b340e908bceae",
"outcomes/submissions.jsonl": "1b38e3b240e49cefd44193d64c4ea3d64a8b75b358c4c430a9b7fdb52fa92815" "outcomes/submissions.jsonl": "1b38e3b240e49cefd44193d64c4ea3d64a8b75b358c4c430a9b7fdb52fa92815"
}, },
"generation": 24428, "generation": 24429,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-13T22:16:17.837103+00:00", "updatedAt": "2026-10-13T22:18:17.360052+00:00",
"writerId": "0b4d13138a434e929040a457f5ff8e93" "writerId": "0b4d13138a434e929040a457f5ff8e93"
} }