state: generation 27679 (intent)
This commit is contained in:
@@ -634,7 +634,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-21T20:03:40.264812+00:00",
|
||||
"generatedAt": "2026-10-21T20:05:26.513530+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 31,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -452,7 +452,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-21T20:03:40.369453+00:00",
|
||||
"generatedAt": "2026-10-21T20:05:26.631841+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-10-21T20:03:40.369453+00:00",
|
||||
"catalogUpdatedAt": "2026-10-21T20:05:26.631841+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-10-21T20:03:46.795448+00:00",
|
||||
"generatedAt": "2026-10-21T20:05:26.631841+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6570,6 +6570,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-10-21T20:03:40.369453+00:00",
|
||||
"taskTreeUpdatedAt": "2026-10-21T20:05:26.631841+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-21T18:04:37.880874+00:00",
|
||||
"lastSyncTime": "2026-10-21T18:04:37.541467+00:00",
|
||||
"generatedAt": "2026-10-21T20:05:26.414132+00:00",
|
||||
"lastSyncTime": "2026-10-21T20:05:26.166988+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -46,33 +46,6 @@
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:mini_k3": {
|
||||
"architectureSignature": "model_type:mini_k3",
|
||||
"architectures": [],
|
||||
"evidenceCount": 5,
|
||||
"expiresAt": "2026-10-21T19:37:12.459191+00:00",
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"latestFailureAt": "2026-09-21T19:37:12.459191+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "mini_k3",
|
||||
"sourceModelIds": [
|
||||
"nkkbr/Mini-K3-1H-decay-g2-v2_C",
|
||||
"nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B",
|
||||
"nkkbr/Mini-K3-1H-attnres-block6-v1_C",
|
||||
"nkkbr/Mini-K3-1H-attnres-standard-v1_B",
|
||||
"nkkbr/Mini-K3-1H-decay-g16-v2_B"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"5006360",
|
||||
"5006359",
|
||||
"5006364",
|
||||
"5006357",
|
||||
"5006356"
|
||||
],
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"ascend_910-b3|vllm|text-generation|model_type:mini_k3": {
|
||||
"architectureSignature": "model_type:mini_k3",
|
||||
"architectures": [],
|
||||
@@ -140,27 +113,6 @@
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:mini_k3": {
|
||||
"architectureSignature": "model_type:mini_k3",
|
||||
"architectures": [],
|
||||
"evidenceCount": 2,
|
||||
"expiresAt": "2026-10-21T19:05:50.437924+00:00",
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"latestFailureAt": "2026-09-21T19:05:50.437924+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "mini_k3",
|
||||
"sourceModelIds": [
|
||||
"nkkbr/Mini-K3-1H-decay-g16-v2_B",
|
||||
"nkkbr/Mini-K3-1H-attnres-block6-v1_C"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"5006050",
|
||||
"5006054"
|
||||
],
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"cambricon_mlu-370-x4|vllm-customized|text-generation|model_type:mini_k3": {
|
||||
"architectureSignature": "model_type:mini_k3",
|
||||
"architectures": [],
|
||||
@@ -260,33 +212,6 @@
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:mini_k3": {
|
||||
"architectureSignature": "model_type:mini_k3",
|
||||
"architectures": [],
|
||||
"evidenceCount": 5,
|
||||
"expiresAt": "2026-10-21T19:52:49.757664+00:00",
|
||||
"framework": "vllm-mlu",
|
||||
"latestFailureAt": "2026-09-21T19:52:49.757664+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "mini_k3",
|
||||
"sourceModelIds": [
|
||||
"nkkbr/Mini-K3-1H-decay-g16-v2_B",
|
||||
"nkkbr/Mini-K3-1H-attnres-block6-v1_C",
|
||||
"nkkbr/Mini-K3-1H-decay-g2-v2_C",
|
||||
"nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C",
|
||||
"nkkbr/Mini-K3-1H-attnres-standard-v1_B"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"5006516",
|
||||
"5006518",
|
||||
"5006512",
|
||||
"5006511",
|
||||
"5006510"
|
||||
],
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
@@ -447,27 +372,6 @@
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"iluvatar_bi-150|vllm_tokenizer_patch|text-generation|architectures:qwen3_5moeforconditionalgeneration": {
|
||||
"architectureSignature": "architectures:qwen3_5moeforconditionalgeneration",
|
||||
"architectures": [
|
||||
"qwen3_5moeforconditionalgeneration"
|
||||
],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-21T18:14:20.635969+00:00",
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"latestFailureAt": "2026-09-21T18:14:20.635969+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "architectures",
|
||||
"modelType": "qwen3_5_moe",
|
||||
"sourceModelIds": [
|
||||
"ornith-ai/Ornith-1.5-35B-A3B-NVFP4"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"5005325"
|
||||
],
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"iluvatar_mrv-100|vllm|text-generation|model_type:gpt_oss": {
|
||||
"architectureSignature": "model_type:gpt_oss",
|
||||
"architectures": [],
|
||||
@@ -529,25 +433,6 @@
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"iluvatar_mrv-100|vllm|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-21T19:52:49.754157+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-21T19:52:49.754157+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5",
|
||||
"sourceModelIds": [
|
||||
"prithivMLmods/Nexus-9B-CodeCore-Merge"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"5006513"
|
||||
],
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"metax_c-500|vllm_tokenizer_patch|text-generation|architectures:spark2_5forcausallm": {
|
||||
"architectureSignature": "architectures:spark2_5forcausallm",
|
||||
"architectures": [
|
||||
@@ -754,18 +639,17 @@
|
||||
}
|
||||
},
|
||||
"architectureCompatibilitySummary": {
|
||||
"activeBlockCount": 36,
|
||||
"activeBlockCount": 31,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 1,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 3,
|
||||
"Ascend_910-b4|vllm_tokenizer_patch": 3,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 2,
|
||||
"Ascend_910-b4|vllm_tokenizer_patch": 2,
|
||||
"Cambricon_mlu-370-x4|vllm": 1,
|
||||
"Cambricon_mlu-370-x4|vllm-customized": 2,
|
||||
"Cambricon_mlu-370-x4|vllm-mlu": 1,
|
||||
"Cambricon_mlu-370-x8|vllm-mlu": 3,
|
||||
"Cambricon_mlu-370-x8|vllm-mlu": 2,
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
|
||||
"Iluvatar_bi-150|vllm_tokenizer_patch": 1,
|
||||
"Iluvatar_mrv-100|vllm": 4,
|
||||
"Iluvatar_mrv-100|vllm": 3,
|
||||
"MetaX_c-500|vllm": 1,
|
||||
"MetaX_c-500|vllm_tokenizer_patch": 4,
|
||||
"Mthreads_s4000|vllm": 3,
|
||||
@@ -2416,10 +2300,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 193,
|
||||
"ambiguous_runtime": 194,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 202,
|
||||
"failureCount": 203,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -2429,8 +2313,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 202,
|
||||
"unresolvedFailureCount": 202
|
||||
"total": 203,
|
||||
"unresolvedFailureCount": 203
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 61,
|
||||
@@ -3604,7 +3488,7 @@
|
||||
"decisionSuccessRate": 0.0359,
|
||||
"decisionTotal": 195,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 430,
|
||||
"ambiguous_runtime": 431,
|
||||
"backend_operator": 11,
|
||||
"framework_architecture_unsupported": 56,
|
||||
"memory_capacity": 11,
|
||||
@@ -3613,15 +3497,15 @@
|
||||
"tokenizer_compatibility": 97,
|
||||
"参数/模板问题": 30
|
||||
},
|
||||
"failureCount": 683,
|
||||
"failureCount": 684,
|
||||
"failureRate": 0.9899,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 35,
|
||||
"successCount": 7,
|
||||
"successRate": 0.0101,
|
||||
"total": 690,
|
||||
"unresolvedFailureCount": 460
|
||||
"total": 691,
|
||||
"unresolvedFailureCount": 461
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 171,
|
||||
@@ -3652,7 +3536,7 @@
|
||||
"unresolvedFailureCount": 339
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-21T18:04:37.866055+00:00",
|
||||
"generatedAt": "2026-10-21T20:05:26.400400+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 132,
|
||||
@@ -3885,7 +3769,7 @@
|
||||
"decisionSuccessRate": 0.066,
|
||||
"decisionTotal": 106,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 282,
|
||||
"ambiguous_runtime": 283,
|
||||
"backend_operator": 23,
|
||||
"framework_architecture_unsupported": 37,
|
||||
"memory_capacity": 3,
|
||||
@@ -3898,15 +3782,15 @@
|
||||
"日志缺失": 1,
|
||||
"验证失败": 23
|
||||
},
|
||||
"failureCount": 459,
|
||||
"failureCount": 460,
|
||||
"failureRate": 0.985,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 7,
|
||||
"successRate": 0.015,
|
||||
"total": 466,
|
||||
"unresolvedFailureCount": 359
|
||||
"total": 467,
|
||||
"unresolvedFailureCount": 360
|
||||
},
|
||||
"Kunlunxin_r-200-8f": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -16838,6 +16722,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cagliostro|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "cagliostro",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cohere2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -25467,14 +25374,14 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"ambiguous_runtime": 7,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 7,
|
||||
"failureCount": 8,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-10-12T18:40:58.271114+00:00",
|
||||
"lastTerminalAt": "2026-10-21T20:05:26.166988+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -25482,8 +25389,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 7
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"MetaX_c-500|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -26624,6 +26531,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cagliostro|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-10-21T20:05:26.166988+00:00",
|
||||
"modelType": "cagliostro",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|k2_horizon|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -46815,6 +46747,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cagliostro|none|28": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 28,
|
||||
"modelType": "cagliostro",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cohere2|none|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -59568,15 +59524,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17936,
|
||||
"totalRecords": 18466,
|
||||
"terminalRecords": 17937,
|
||||
"totalRecords": 18467,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6346,
|
||||
"decisionFailureRate": 0.8655,
|
||||
"decisionSuccessRate": 0.1345,
|
||||
"decisionTotal": 7332,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4660,
|
||||
"ambiguous_runtime": 4661,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 135,
|
||||
@@ -59592,77 +59548,77 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16950,
|
||||
"failureCount": 16951,
|
||||
"failureRate": 0.945,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 971,
|
||||
"successCount": 986,
|
||||
"successRate": 0.055,
|
||||
"total": 17936,
|
||||
"unresolvedFailureCount": 9633
|
||||
"total": 17937,
|
||||
"unresolvedFailureCount": 9634
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b4 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 Vastai_va16 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 MetaX_c-500 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 hygon_k100-ai 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 Cambricon_mlu-370-x8 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 Iluvatar_bi-150 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 hygon_k100-ai 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-b4 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 Iluvatar_mrv-100 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_bi-150 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 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 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。",
|
||||
"组合 Iluvatar_bi-150|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-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 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 Ascend_910-b4|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-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 Iluvatar_bi-150|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 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_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 MetaX_c-500|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 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 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|llamacpp|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-mlu|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|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-customized|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|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-x4|vllm-mlu|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 Sunrise_pt-200-x1|vllm|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 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 Kunlunxin_p-800|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 MetaX_c-500|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 MetaX_c-500|vllm|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 Iluvatar_bi-150|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|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 Mthreads_s4000|llamacpp|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|llamacpp|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|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Kunlunxin_p-800|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 Sunrise_pt-200-x1|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 Ascend_910-b4|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 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 Sunrise_pt-200-x1|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 Iluvatar_mrv-100|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 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 Biren_166m|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 Vastai_va16|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 Iluvatar_bi-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 Iluvatar_mrv-100|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 Biren_166m|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 hygon_k100-ai|vllm|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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|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|llamacpp|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 Sunrise_pt-200-x1|vllm|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 Mthreads_s4000|llamacpp|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|vllm-customized|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|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|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 MetaX_c-500|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 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 MetaX_c-500|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 Mthreads_s4000|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 Iluvatar_bi-150|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 Biren_166m|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 Sunrise_pt-200-x1|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 Biren_166m|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 Sunrise_pt-200-x1|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 Iluvatar_bi-150|transformers|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 Cambricon_mlu-370-x4|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 Iluvatar_bi-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 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 Kunlunxin_p-800|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 MetaX_c-500|vllm|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 Cambricon_mlu-370-x8|vllm-mlu|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|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 Iluvatar_mrv-100|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_bi-150|vllm|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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|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|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|vllm-mlu|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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 18466,
|
||||
"summarizedRecords": 18467,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -101,6 +101,7 @@
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T13:04:00.870447+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-08T04:35:43.854342+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5368938", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T18:42:58.165451+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-08T04:19:38.748920+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5368612", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T15:45:17.258678+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-08T03:55:00.884003+00:00", "targetGpu": "MetaX_c-500", "taskId": "5367428", "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_fix_tokenizer", "lastSyncTime": "2026-10-21T20:05:26.166988+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "failed", "status": "success", "submitTime": "2026-10-07T20:33:02.765344+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361260", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-12T18:40:58.271114+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20984462832, "estimatedRequiredGiB": 23.486, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21014909211, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:qwen3-next", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:mixture-of-experts"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-23T21:42:41.557218+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 21014909211}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T20:31:42.948575+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361250", "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_fix_tokenizer", "lastSyncTime": "2026-10-10T18:12:14.470925+00:00", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "failed", "status": "success", "submitTime": "2026-10-07T20:31:42.848435+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361249", "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_fix_tokenizer", "lastSyncTime": "2026-10-10T08:31:17.760249+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "failed", "status": "success", "submitTime": "2026-10-07T20:31:42.847347+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361257", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:09:53.041493+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.345125+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319936", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T12:22:04.159158+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.267901+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319934", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T12:22:04.159226+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.264946+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319930", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T12:22:04.159110+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.262829+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319938", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
@@ -3689,6 +3689,18 @@
|
||||
{"batchId": "29dfd316024d45d0bc40a8a15d571490", "completedAt": "2026-10-21T18:39:53.122734+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:39:50.606215+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ff53c7e135344f939b2cef574a485ddc", "lastModified": "2026-10-21T15:40:57+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Explore-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-21T20:03:54.690114+00:00", "repoId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5699620", "taskType": "text-generation"}
|
||||
{"batchId": "9c505c9d159f4f8495bc5e31e8bb24b0", "completedAt": "2026-10-21T18:42:34.650485+00:00", "configFingerprint": "a1180a720dd471c32059d347c8965c5b18df1ca663ca61c609333bb476be5117", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:42:32.111209+00:00", "framework": "llamacpp", "intentId": "f325a603297d4a3e9b0ed6bc55a7280c", "lastModified": "2026-10-21T18:16:46+00:00", "modelAddress": "https://modelscope.cn/models/AtomicChat/Qwen3.5-9B-DFlash-GGUF", "reason": null, "reconciledAt": "2026-10-21T20:03:54.690985+00:00", "repoId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5699676", "taskType": "text-generation"}
|
||||
{"batchId": "5bb2c5352b644790992acdf3f4f523ff", "completedAt": "2026-10-21T19:49:02.957262+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T19:48:50.055809+00:00", "framework": "vllm_tokenizer_patch", "intentId": "933b46fdd9a54b24a06b04b46a445f54", "lastModified": "2026-10-19T18:03:21+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-21T20:03:54.690111+00:00", "repoId": "cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5700656", "taskType": "text-generation"}
|
||||
{"batchId": "274191559aaa46e2a2af1ebebf669c70", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:05:28.105826+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d69138d827b54d59a4936604e74b38a3", "lastModified": "2026-10-21T16:31:51+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit", "repoId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "274191559aaa46e2a2af1ebebf669c70", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:05:28.105924+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bedf41b1dfd64075bef3ac23786f96bc", "lastModified": "2026-10-21T19:08:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "repoId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "274191559aaa46e2a2af1ebebf669c70", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:05:28.105971+00:00", "framework": "vllm_tokenizer_patch", "intentId": "73306b12668b4fe18948aa089eea7193", "lastModified": "2026-10-21T16:46:52+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Seed-OSS-36B-Instruct-AWQ-8bit", "repoId": "cyankiwi/Seed-OSS-36B-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "274191559aaa46e2a2af1ebebf669c70", "configFingerprint": "705b8b3614c86a1ac722c97f43e177e84ca20282e9799fffb1b890510d641728", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:05:28.106015+00:00", "framework": "llamacpp", "intentId": "621d850400014d5d87bad250977a5ded", "lastModified": "2026-10-21T18:16:46+00:00", "modelAddress": "https://modelscope.cn/models/AtomicChat/Qwen3.5-9B-DFlash-GGUF", "repoId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "274191559aaa46e2a2af1ebebf669c70", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:05:28.106068+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f2f508b0a15f4f93b1b250989d73b805", "lastModified": "2026-10-21T16:33:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "274191559aaa46e2a2af1ebebf669c70", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:05:28.106122+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f8a2c09aab2a4f8d8cc8802365711947", "lastModified": "2026-10-21T17:03:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniCPM-SALA-AWQ-4bit", "repoId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "274191559aaa46e2a2af1ebebf669c70", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:05:28.106172+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f03bc59f66014c889314fcfdbe38d215", "lastModified": "2026-10-21T16:21:36+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "274191559aaa46e2a2af1ebebf669c70", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:05:28.106228+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f2a83862b7984d5ab013193ad27d6103", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "274191559aaa46e2a2af1ebebf669c70", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:05:28.106277+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a400d5e76bd74c2aa756ea4a004f42fc", "lastModified": "2026-10-21T16:56:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "274191559aaa46e2a2af1ebebf669c70", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:05:28.106325+00:00", "framework": "vllm_tokenizer_patch", "intentId": "65f0c58fbe3d45f1a6b23780fc15f27a", "lastModified": "2026-10-21T15:53:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "274191559aaa46e2a2af1ebebf669c70", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:05:28.106373+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fd5daae8d4644089899dfd0ecbf7df42", "lastModified": "2026-10-21T16:38:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "274191559aaa46e2a2af1ebebf669c70", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:05:28.106422+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8313ad75e45d45bc82dfeb5b57239d9e", "lastModified": "2026-10-21T16:49:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "4c5de8442fce4a17afae1abfb9b3a0b0", "completedAt": "2026-10-21T20:03:51.441248+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:03:48.789321+00:00", "framework": "vllm_tokenizer_patch", "intentId": "298d52b5b1f7444ba2ac43d65f8e181a", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "4c5de8442fce4a17afae1abfb9b3a0b0", "completedAt": "2026-10-21T20:03:51.441245+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:03:48.789272+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fc45587492794779b658e1b5918693c2", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "4c5de8442fce4a17afae1abfb9b3a0b0", "completedAt": "2026-10-21T20:03:51.441243+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:03:48.789223+00:00", "framework": "vllm_tokenizer_patch", "intentId": "41fe7e18554a425c886a998f1f68b604", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "da4d70c539c4502adb9842c0b2676d0123dadc5abe8291ec5221f76ea61555e2",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "d5a29feee739fba0427d52477241e61adf1a7f70c841d98b87931b3d7477b7c0",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "3bd8bd419bd5485f3c86b76c299665c1e5da039e26f751ea33733e48d8106f15",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "ea9e546504db27344df17569fa84bd5832c7118e0d7d03954679906cbd0af0bc",
|
||||
".modelhub_state/official_capabilities.json": "9bad8af6d8967805d37d3ad5b4419ef77561e07e99fd427b2b84f4bdae086ed0",
|
||||
".modelhub_state/outcome_checkpoint.json": "e482d70af5c40c026fa1d6bc289f21838edd60836ab4c12582c293a2deab2cf3",
|
||||
".modelhub_state/market_intelligence.json": "0910ab5ffa537a5ecbf366894eabcdd44c365facf135fa480db1951be7dc397d",
|
||||
".modelhub_state/official_capabilities.json": "2e172de3eb4038d80aedfef8e3ce2f0a5bc9110071733be3300f8ccaf3d58d53",
|
||||
".modelhub_state/outcome_checkpoint.json": "a45774b8e5afa434df824dca06e79bb460e29f6f4ca8bbc6754ad850ac92feef",
|
||||
".modelhub_state/queue_cleanup_latest.json": "7b166c835c959d893d154af368c56271091deec3c0322dd26922969a80cb7cac",
|
||||
".modelhub_state/recent_outcomes.jsonl": "24ec76395955db5316ea193aa6a33685ef4c7bcace5288c8643bcccd81ff5285",
|
||||
".modelhub_state/recent_outcomes.jsonl": "02717b4beeab48c2d89f3337e217ef9c68f7ff9f1fe254c7b49f7a949995eba3",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "25c304911dff694ce3ba88646f28fe3242e831d59700e18a2f1d04a1a91b423a",
|
||||
".modelhub_state/recovery_intents.jsonl": "ecc87619307a33b3a3881603e91023541523d489ec1106962a7655f1e9f6b7c1",
|
||||
".modelhub_state/recovery_intents.jsonl": "85c33c4b111d1edb3af36e505fac3dd04bc57f0c76e95d65a31aec19eeda3669",
|
||||
".modelhub_state/routing_intelligence.json": "0e7f4e4b0fa0f5c5e6bccb1fc88e166450b702f12bc19e30a10d0b1823595973",
|
||||
".modelhub_state/submission_exclusions.jsonl": "e2677e09d968a0c44c65d7c030b9c8ea2c9d39dc378ce302c2a309ab54d600d9",
|
||||
".modelhub_state/worker_crashes.jsonl": "7ec5c580696be9e252968d3b24d3fe50028c3bb63d0549fafeb5a34732dade21",
|
||||
"ledger/submissions.jsonl": "4e427bfb2f4f876e36173baa20311ad902269dcc0a40d271242957fbaf39c8e0",
|
||||
"outcomes/submissions.jsonl": "699429b211b4602503b6656ee3fe901665b167fe3962042c1bf97814f1521e90"
|
||||
"outcomes/submissions.jsonl": "afb50099bcb3fb54e8fdf7ce9e1be2ff226b4191ed65bf594b4f4267b9b9ad31"
|
||||
},
|
||||
"generation": 27678,
|
||||
"phase": "cycle",
|
||||
"generation": 27679,
|
||||
"phase": "intent",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-10-21T20:03:54.929382+00:00",
|
||||
"updatedAt": "2026-10-21T20:05:28.259871+00:00",
|
||||
"writerId": "d3d6980b05264495beb8a7e113a1076c"
|
||||
}
|
||||
|
||||
@@ -668,7 +668,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T04:46:03.168167+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T20:31:42.756521+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361247", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T04:46:03.168208+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T20:31:42.754091+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361255", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T04:46:03.168194+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "b19172cc089e3ab5863a7f6499e4833c8fad38ee16cd9107fd0b438c645cd77f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T20:31:42.952762+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361252", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T04:46:03.168136+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T20:33:02.765344+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361260", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T04:46:03.168013+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960168568, "estimatedRequiredGiB": 2.344, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2097293495, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2097293495}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T20:33:02.946453+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361265", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T04:46:03.168069+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T20:33:02.961865+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361263", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T04:46:03.168187+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145035684, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1605333250, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8145035684}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T20:33:02.951500+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361266", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -1082,7 +1081,7 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-21T16:14:40.355786+00:00", "modelId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "b8a926f4d98c4c17ed728affade2dfee1910e905840c16a7c6d35cdf073f1b9a", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2959518912, "estimatedRequiredGiB": 11.359, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10163561932, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:dflash2", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10163561932}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T08:13:50.255199+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5691062", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T17:53:42.338011+00:00", "modelId": "cpatonn-mirror/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3NextForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 49231450912, "estimatedRequiredGiB": 55.063, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_next", "modelscopeFileSize": 49269386372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 81324862720, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_next", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 49269386372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T09:52:13.230435+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5692453", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T18:04:37.541436+00:00", "modelId": "iluvatar-corex/Qwen3-8B-W8A8", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9441379272, "estimatedRequiredGiB": 10.569, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 9457348916, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9457348916}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T10:03:53.143948+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5692570", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064333187, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 33064333187}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T12:05:06.542231+00:00", "targetGpu": "MetaX_c-500", "taskId": "5694040", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T20:05:26.166962+00:00", "modelId": "cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064333187, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 33064333187}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T12:05:06.542231+00:00", "targetGpu": "MetaX_c-500", "taskId": "5694040", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459873078, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3459873078}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T12:36:29.041842+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5694581", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25339204672, "estimatedRequiredGiB": 28.332, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25350742978, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22705296512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25350742978}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T13:05:07.628503+00:00", "targetGpu": "MetaX_c-500", "taskId": "5694815", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26166907992, "estimatedRequiredGiB": 29.255, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 26176736582, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26176736582}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T13:16:58.055588+00:00", "targetGpu": "MetaX_c-500", "taskId": "5695060", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user