state: generation 8678 (cycle)

This commit is contained in:
2026-09-17 10:19:50 +00:00
parent c950e3bb58
commit 3596b18377
10 changed files with 2068 additions and 1978 deletions

View File

@@ -1741,7 +1741,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-17T10:17:44.235931+00:00",
"generatedAt": "2026-09-17T10:19:49.648809+00:00",
"summary": {
"activeBlockCount": 84,
"byGpuFramework": {

View File

@@ -75,7 +75,7 @@
"7": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 634,
"listingErrors": 635,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 7,
"nextAccountIndex": 8,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-17T10:17:44.208686+00:00",
"updatedAt": "2026-09-17T10:19:49.621680+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-17T10:15:29.300761+00:00",
"generatedAt": "2026-09-17T10:17:47.830588+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-17T10:10:02.916569+00:00",
"lastSyncTime": "2026-09-17T10:10:02.608119+00:00",
"generatedAt": "2026-09-17T10:17:47.784818+00:00",
"lastSyncTime": "2026-09-17T10:17:47.519781+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1810,25 +1810,25 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 7,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 8,
"attributableFailureCount": 9,
"decisionFailureRate": 0.9,
"decisionSuccessRate": 0.1,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 7
"framework_architecture_unsupported": 9
},
"failureCount": 12,
"failureRate": 0.9231,
"failureCount": 14,
"failureRate": 0.9333,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0769,
"successRate": 0.0667,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 13,
"total": 15,
"unresolvedFailureCount": 5
},
"Ascend_910-b3|vllm|text-generation": {
@@ -2953,48 +2953,48 @@
"unresolvedFailureCount": 72
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 10,
"decisionFailureRate": 0.9091,
"decisionSuccessRate": 0.0909,
"decisionTotal": 11,
"attributableFailureCount": 12,
"decisionFailureRate": 0.9231,
"decisionSuccessRate": 0.0769,
"decisionTotal": 13,
"failureBreakdown": {
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 10
"framework_architecture_unsupported": 12
},
"failureCount": 18,
"failureRate": 0.9474,
"failureCount": 20,
"failureRate": 0.9524,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0526,
"total": 19,
"successRate": 0.0476,
"total": 21,
"unresolvedFailureCount": 8
}
},
"generatedAt": "2026-09-17T10:10:02.910840+00:00",
"generatedAt": "2026-09-17T10:17:47.778110+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 54,
"decisionFailureRate": 0.9474,
"decisionSuccessRate": 0.0526,
"decisionTotal": 57,
"attributableFailureCount": 56,
"decisionFailureRate": 0.9492,
"decisionSuccessRate": 0.0508,
"decisionTotal": 59,
"failureBreakdown": {
"ambiguous_runtime": 37,
"framework_architecture_unsupported": 52,
"framework_architecture_unsupported": 54,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 10,
"验证失败": 27
},
"failureCount": 128,
"failureRate": 0.9771,
"failureCount": 130,
"failureRate": 0.9774,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0229,
"total": 131,
"successRate": 0.0226,
"total": 133,
"unresolvedFailureCount": 74
},
"Ascend_910-b4": {
@@ -3486,6 +3486,52 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -7767,6 +7813,54 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|29": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -12525,17 +12619,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2116,
"totalRecords": 2219,
"terminalRecords": 2118,
"totalRecords": 2221,
"totals": {
"attributableFailureCount": 690,
"decisionFailureRate": 0.8835,
"decisionSuccessRate": 0.1165,
"decisionTotal": 781,
"attributableFailureCount": 692,
"decisionFailureRate": 0.8838,
"decisionSuccessRate": 0.1162,
"decisionTotal": 783,
"failureBreakdown": {
"ambiguous_runtime": 519,
"backend_operator": 48,
"framework_architecture_unsupported": 459,
"framework_architecture_unsupported": 461,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
@@ -12545,14 +12639,14 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2025,
"failureCount": 2027,
"failureRate": 0.957,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 91,
"successRate": 0.043,
"total": 2116,
"total": 2118,
"unresolvedFailureCount": 1325
},
"warnings": [
@@ -12560,14 +12654,14 @@
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 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 hygon_k100-ai 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 Ascend_910-b3 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 Vastai_va16 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。",
"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 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 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。",
@@ -12593,6 +12687,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2219,
"summarizedRecords": 2221,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -100,7 +100,6 @@
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-08T07:30:11.995863+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4713445", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T09:42:38.119885+00:00", "targetGpu": "Vastai_va16", "taskId": "4716367", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T09:50:25.159456+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4716485", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T10:18:12.673769+00:00", "targetGpu": "Biren_166m", "taskId": "4716910", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-gguf", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "submitTime": "2026-09-08T10:26:22.306973+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4717031", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T10:53:08.602969+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4717458", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "submitTime": "2026-09-08T12:23:10.100285+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4718771", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
@@ -203,7 +202,6 @@
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-08T23:02:45.686402+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729506", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-08T23:02:45.691566+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729498", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-08T23:02:45.694196+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729499", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-08T23:02:45.696067+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729497", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "submitTime": "2026-09-08T23:02:51.785155+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729509", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "modelId": "siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "submitTime": "2026-09-08T23:02:51.924564+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729534", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/dealignai/MiniMax-M2.7-JANGTQ-CRACK", "modelId": "dealignai/MiniMax-M2.7-JANGTQ-CRACK", "submitTime": "2026-09-08T23:02:52.031559+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729530", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "0e09aa60ca110a22979653b44079e366782c07e1dfe0988c5e046ebfac662715",
".modelhub_state/architecture_history_backfill.json": "cd2941820c9f5fd91527f975c81bc2aa5973af779763f29d6177368c86da8613",
".modelhub_state/market_intelligence.json": "423256316afc4d44b4c3a1a659a95ab7e2e843fbf48241b7361368ae9fcf5401",
".modelhub_state/official_capabilities.json": "6ddad2bb769bce278aa7397851b5e1841e134097e397eb619af35332d15072c7",
".modelhub_state/outcome_checkpoint.json": "f9e437879143fb79c16bb0e1f613b17fa7e42f1bd14ff5e425b95f2212830ce1",
".modelhub_state/architecture_compatibility_blacklist.json": "70ae7278ad2ec2ccc79042914a81de1ce849d88a3435c47588f85fd5028efbd9",
".modelhub_state/architecture_history_backfill.json": "e300100c674114aad90ce265dbd781fbca6fb19fef42b2265c972b16084384e8",
".modelhub_state/market_intelligence.json": "9a1ff9bce3914cbc64c969a416bf6f346810be185f6e983b47ce59090bfd222e",
".modelhub_state/official_capabilities.json": "4de00ee13bac3f33f5c7c93db5764ab41e220bad96fc7f6f00b72e54ce41c1d5",
".modelhub_state/outcome_checkpoint.json": "b961ad26c05b0d0518411bd4660a0bf16c56ce861c235a6625949766de033c6e",
".modelhub_state/queue_cleanup_latest.json": "4be02869ade05ead6def3f33db6297b95930841c24c0c7cab3372f7790acadd8",
".modelhub_state/recent_outcomes.jsonl": "178cc994b45fb46d1998a6236acd729b76eefa9cb0c6f5da9a9b2e12791ade7a",
".modelhub_state/recovery_active_tasks.jsonl": "1ce48418e3a2b51bb349602783d0097cf99d118352a714db324e118f33c20d88",
".modelhub_state/recovery_intents.jsonl": "6219d0c84972b898f7f082e8223582537ddb3b0bb5bffbe3b3e0928f513c46d9",
".modelhub_state/recovery_active_tasks.jsonl": "af11f3de20d0436dea3b933337ffd664b45ddd2d986a11f23adf8589ebea7962",
".modelhub_state/recovery_intents.jsonl": "495ff05cce455cfeb0cead9f48ffd2fddab25bc1b984678c585794f4274c99cd",
".modelhub_state/routing_intelligence.json": "d95dfab94e0072d37f9ab4091daff9c5e06f9f24d6011b91b19edf0723935555",
".modelhub_state/submission_exclusions.jsonl": "a0cb4e822e4b6d26c26c3bf22698cacbab31f2df5f3402ecf04fdfb3a3577ef7",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "d1891f6e7d6fde60789ed29489de171bb0402528d98c6cd2ee00b01fa941644b",
"outcomes/submissions.jsonl": "f7ef74703625e61fde186fd439a3a4b0beb2b4c301ce9e07f25965a3595a3609"
"ledger/submissions.jsonl": "310288dfd3eb59578d7c2590718f462da76b6813aa93e183c50e176521e28e66",
"outcomes/submissions.jsonl": "0af800a83732ccb7db33e5b0513443c69d51b4471d4ea381400917c0a3f7894d"
},
"generation": 8677,
"generation": 8678,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-17T10:17:44.873304+00:00",
"updatedAt": "2026-09-17T10:19:50.356566+00:00",
"writerId": "eccb3e0018f640d19e578c271a207b5c"
}

View File

@@ -82,7 +82,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:31:35.012291+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:25:37.107095+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678756", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:31:35.012329+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9023443508, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:25:37.111002+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678760", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T06:07:37.712071+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9339955920, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:math", "custom_tag:stem", "custom_tag:mtp", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9339955920}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:55:23.563817+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679536", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-07T06:07:37.712005+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T22:04:12.072657+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4679733", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T17:31:43.302628+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9fba363aef42aed2b52f3be34868ab5830a7c956f45e65fceed6561122eb8743", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 14.087, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8229925227, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 12604946379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T09:29:07.790789+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4691709", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T18:00:51.826326+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8bb72add25c6bbefdaaa3d4fc9d420176b02cfa13433975a607b2e5a23d944d6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 14.087, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8229925227, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 12604946379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T09:53:15.317620+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4692145", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T18:18:26.905231+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c8002a19ceb3b3bde544f5a0cc84985eeda610b7a8666758689c1b5d9da4f882", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 14.087, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8229925227, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 12604946379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T10:17:32.532423+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4692612", "taskType": "text-generation", "verifyResult": null}
@@ -98,7 +97,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T23:43:05.101242+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T15:35:43.483187+00:00", "targetGpu": "MetaX_c-500", "taskId": "4698954", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-08T00:02:57.396828+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T16:01:34.238434+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4699472", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T00:12:24.015192+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T16:06:40.552870+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4699585", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T00:32:26.904342+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T16:31:45.492609+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4700151", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T01:37:35.725250+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0e96112008e09ac1841408e47a35f72b68023fca4efc76695e6eb96ba540ba1c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6348507357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T17:27:44.564043+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4701029", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T04:10:28.996444+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T19:56:19.088834+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4703149", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T09:05:31.097982+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "cfe08978e062dae728d260488110f70f7f12953c8f377a0f9c0a93bc3f6b0862", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.371, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280253884, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280253884}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T00:43:38.323540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4707395", "taskType": "text-generation", "verifyResult": null}