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

state: generation 25830 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-10-19 14:44:16 +00:00
parent eb8a95f6f0
commit fe9e155fcc
7 changed files with 1614 additions and 1489 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2354,7 +2354,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-19T14:04:19.479624+00:00", "generatedAt": "2026-10-19T14:40:29.846875+00:00",
"summary": { "summary": {
"activeBlockCount": 117, "activeBlockCount": 117,
"byGpuFramework": { "byGpuFramework": {

603
.modelhub_state/market_intelligence.json
View File

File diff suppressed because it is too large Load Diff

2332
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

134
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-19T14:04:19.379277+00:00", "generatedAt": "2026-10-19T14:40:29.759649+00:00",
"lastSyncTime": "2026-10-19T14:04:19.066017+00:00", "lastSyncTime": "2026-10-19T14:40:29.465648+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -4541,32 +4541,32 @@
"backend_operator": 11, "backend_operator": 11,
"framework_architecture_unsupported": 29, "framework_architecture_unsupported": 29,
"memory_capacity": 1, "memory_capacity": 1,
"platform_infrastructure": 34, "platform_infrastructure": 35,
"tokenizer_compatibility": 97, "tokenizer_compatibility": 97,
"参数/模板问题": 10 "参数/模板问题": 10
}, },
"failureCount": 185, "failureCount": 186,
"failureRate": 0.9946, "failureRate": 0.9947,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 34, "platformFailureCount": 35,
"successCount": 1, "successCount": 1,
"successRate": 0.0054, "successRate": 0.0053,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 186, "total": 187,
"unresolvedFailureCount": 13 "unresolvedFailureCount": 13
}, },
"Sunrise_pt-200-x1|vllm|text-generation": { "Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 633, "attributableFailureCount": 634,
"decisionFailureRate": 0.9829, "decisionFailureRate": 0.9829,
"decisionSuccessRate": 0.0171, "decisionSuccessRate": 0.0171,
"decisionTotal": 644, "decisionTotal": 645,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 109, "ambiguous_runtime": 109,
"architecture_compatibility": 43, "architecture_compatibility": 43,
"backend_operator": 32, "backend_operator": 33,
"context_length": 34, "context_length": 34,
"framework_architecture_unsupported": 153, "framework_architecture_unsupported": 153,
"memory_capacity": 113, "memory_capacity": 113,
@@ -4576,17 +4576,17 @@
"tokenizer_compatibility": 182, "tokenizer_compatibility": 182,
"参数/模板问题": 9 "参数/模板问题": 9
}, },
"failureCount": 975, "failureCount": 976,
"failureRate": 0.9888, "failureRate": 0.9889,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 224, "platformFailureCount": 224,
"successCount": 11, "successCount": 11,
"successRate": 0.0112, "successRate": 0.0111,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 986, "total": 987,
"unresolvedFailureCount": 118 "unresolvedFailureCount": 118
}, },
"Sunrise_pt-200-x1|vllm|unknown": { "Sunrise_pt-200-x1|vllm|unknown": {
@@ -5089,15 +5089,15 @@
"unresolvedFailureCount": 6552 "unresolvedFailureCount": 6552
}, },
"vllm": { "vllm": {
"attributableFailureCount": 3704, "attributableFailureCount": 3705,
"decisionFailureRate": 0.9709, "decisionFailureRate": 0.9709,
"decisionSuccessRate": 0.0291, "decisionSuccessRate": 0.0291,
"decisionTotal": 3815, "decisionTotal": 3816,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1606, "ambiguous_runtime": 1606,
"architecture_compatibility": 112, "architecture_compatibility": 112,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 97, "backend_operator": 98,
"context_length": 161, "context_length": 161,
"framework_architecture_unsupported": 1417, "framework_architecture_unsupported": 1417,
"memory_capacity": 725, "memory_capacity": 725,
@@ -5108,14 +5108,14 @@
"tokenizer_compatibility": 425, "tokenizer_compatibility": 425,
"参数/模板问题": 89 "参数/模板问题": 89
}, },
"failureCount": 6287, "failureCount": 6288,
"failureRate": 0.9827, "failureRate": 0.9827,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 888, "platformFailureCount": 888,
"successCount": 111, "successCount": 111,
"successRate": 0.0173, "successRate": 0.0173,
"total": 6398, "total": 6399,
"unresolvedFailureCount": 1695 "unresolvedFailureCount": 1695
}, },
"vllm-customized": { "vllm-customized": {
@@ -5223,18 +5223,18 @@
"framework_architecture_unsupported": 55, "framework_architecture_unsupported": 55,
"memory_capacity": 11, "memory_capacity": 11,
"model_load": 13, "model_load": 13,
"platform_infrastructure": 34, "platform_infrastructure": 35,
"tokenizer_compatibility": 97, "tokenizer_compatibility": 97,
"参数/模板问题": 28 "参数/模板问题": 28
}, },
"failureCount": 671, "failureCount": 672,
"failureRate": 0.9911, "failureRate": 0.9912,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 34, "platformFailureCount": 35,
"successCount": 6, "successCount": 6,
"successRate": 0.0089, "successRate": 0.0088,
"total": 677, "total": 678,
"unresolvedFailureCount": 450 "unresolvedFailureCount": 450
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
@@ -5266,7 +5266,7 @@
"unresolvedFailureCount": 338 "unresolvedFailureCount": 338
} }
}, },
"generatedAt": "2026-10-19T14:04:19.361959+00:00", "generatedAt": "2026-10-19T14:40:29.745960+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 132, "attributableFailureCount": 132,
@@ -5603,32 +5603,32 @@
"unresolvedFailureCount": 332 "unresolvedFailureCount": 332
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"attributableFailureCount": 790, "attributableFailureCount": 791,
"decisionFailureRate": 0.8827, "decisionFailureRate": 0.8828,
"decisionSuccessRate": 0.1173, "decisionSuccessRate": 0.1172,
"decisionTotal": 895, "decisionTotal": 896,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 165, "ambiguous_runtime": 165,
"architecture_compatibility": 44, "architecture_compatibility": 44,
"backend_operator": 43, "backend_operator": 44,
"context_length": 39, "context_length": 39,
"framework_architecture_unsupported": 184, "framework_architecture_unsupported": 184,
"memory_capacity": 114, "memory_capacity": 114,
"platform_infrastructure": 258, "platform_infrastructure": 259,
"repository_structure": 83, "repository_structure": 83,
"runtime_memory": 1, "runtime_memory": 1,
"tokenizer_compatibility": 282, "tokenizer_compatibility": 282,
"参数/模板问题": 232, "参数/模板问题": 232,
"验证失败": 32 "验证失败": 32
}, },
"failureCount": 1477, "failureCount": 1479,
"failureRate": 0.9336, "failureRate": 0.9337,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 258, "platformFailureCount": 259,
"successCount": 105, "successCount": 105,
"successRate": 0.0664, "successRate": 0.0663,
"total": 1582, "total": 1584,
"unresolvedFailureCount": 429 "unresolvedFailureCount": 429
}, },
"Vastai_va16": { "Vastai_va16": {
@@ -23363,22 +23363,22 @@
"decisionTotal": 8, "decisionTotal": 8,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 8, "framework_architecture_unsupported": 8,
"platform_infrastructure": 2, "platform_infrastructure": 3,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 11, "failureCount": 12,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5_moe", "modelType": "qwen3_5_moe",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 3,
"quantizationMethod": "none", "quantizationMethod": "none",
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 11, "total": 12,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
@@ -23729,14 +23729,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|llama|awq": { "Sunrise_pt-200-x1|vllm|text-generation|llama|awq": {
"attributableFailureCount": 3, "attributableFailureCount": 4,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 3, "decisionTotal": 4,
"failureBreakdown": { "failureBreakdown": {
"backend_operator": 3 "backend_operator": 4
}, },
"failureCount": 3, "failureCount": 4,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"modelType": "llama", "modelType": "llama",
@@ -23748,7 +23748,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 3, "total": 4,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|llama|bitsandbytes": { "Sunrise_pt-200-x1|vllm|text-generation|llama|bitsandbytes": {
@@ -55416,23 +55416,23 @@
"decisionTotal": 3, "decisionTotal": 3,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 3, "framework_architecture_unsupported": 3,
"platform_infrastructure": 1, "platform_infrastructure": 2,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 5, "failureCount": 6,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34, "loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_moe", "modelType": "qwen3_5_moe",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 2,
"quantizationMethod": "none", "quantizationMethod": "none",
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 5, "total": 6,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|35": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|35": {
@@ -55917,14 +55917,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|llama|awq|32": { "Sunrise_pt-200-x1|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 2, "attributableFailureCount": 3,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 3,
"failureBreakdown": { "failureBreakdown": {
"backend_operator": 2 "backend_operator": 3
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"loadSizeLog2Bucket": 32, "loadSizeLog2Bucket": 32,
@@ -55937,7 +55937,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|llama|awq|33": { "Sunrise_pt-200-x1|vllm|text-generation|llama|awq|33": {
@@ -60045,23 +60045,23 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17903, "terminalRecords": 17905,
"totalRecords": 18432, "totalRecords": 18434,
"totals": { "totals": {
"attributableFailureCount": 6337, "attributableFailureCount": 6338,
"decisionFailureRate": 0.8655, "decisionFailureRate": 0.8655,
"decisionSuccessRate": 0.1345, "decisionSuccessRate": 0.1345,
"decisionTotal": 7322, "decisionTotal": 7323,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4643, "ambiguous_runtime": 4643,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 134, "backend_operator": 135,
"context_length": 327, "context_length": 327,
"framework_architecture_unsupported": 2342, "framework_architecture_unsupported": 2342,
"memory_capacity": 1207, "memory_capacity": 1207,
"model_load": 573, "model_load": 573,
"platform_infrastructure": 970, "platform_infrastructure": 971,
"repository_structure": 742, "repository_structure": 742,
"runtime_memory": 101, "runtime_memory": 101,
"tokenizer_compatibility": 696, "tokenizer_compatibility": 696,
@@ -60069,18 +60069,19 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16918, "failureCount": 16920,
"failureRate": 0.945, "failureRate": 0.945,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 970, "platformFailureCount": 971,
"successCount": 985, "successCount": 985,
"successRate": 0.055, "successRate": 0.055,
"total": 17903, "total": 17905,
"unresolvedFailureCount": 9611 "unresolvedFailureCount": 9611
}, },
"warnings": [ "warnings": [
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 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 Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -60089,7 +60090,6 @@
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 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 Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -60140,6 +60140,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 18432, "summarizedRecords": 18434,
"version": 1 "version": 1
} }

12
.modelhub_state/recovery_intents.jsonl
View File

@@ -3645,6 +3645,18 @@
{"batchId": "dc8943324fd24878926b05411e7010b6", "completedAt": "2026-10-19T05:42:22.143459+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T05:16:59.066933+00:00", "framework": "vllm_tokenizer_patch", "intentId": "554b81fb9c1a4d1dab8ccec278f37473", "lastModified": "2026-10-15T14:05:57+00:00", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Diplodocus-preview-JANG_6M", "reason": null, "reconciledAt": "2026-10-19T14:33:14.391932+00:00", "repoId": "OsaurusAI/Diplodocus-preview-JANG_6M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5645005", "taskType": "text-generation"} {"batchId": "dc8943324fd24878926b05411e7010b6", "completedAt": "2026-10-19T05:42:22.143459+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T05:16:59.066933+00:00", "framework": "vllm_tokenizer_patch", "intentId": "554b81fb9c1a4d1dab8ccec278f37473", "lastModified": "2026-10-15T14:05:57+00:00", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Diplodocus-preview-JANG_6M", "reason": null, "reconciledAt": "2026-10-19T14:33:14.391932+00:00", "repoId": "OsaurusAI/Diplodocus-preview-JANG_6M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5645005", "taskType": "text-generation"}
{"batchId": "7d8714bb31484a34b25b1e9218a6bd5f", "completedAt": "2026-10-19T05:49:46.882158+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T05:48:25.746255+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0512ce8e35fc4e3993253c3b1048dc20", "lastModified": "2026-10-19T05:33:13+00:00", "modelAddress": "https://modelscope.cn/models/hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "reason": null, "reconciledAt": "2026-10-19T14:33:14.390524+00:00", "repoId": "hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5645467", "taskType": "text-generation"} {"batchId": "7d8714bb31484a34b25b1e9218a6bd5f", "completedAt": "2026-10-19T05:49:46.882158+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T05:48:25.746255+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0512ce8e35fc4e3993253c3b1048dc20", "lastModified": "2026-10-19T05:33:13+00:00", "modelAddress": "https://modelscope.cn/models/hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "reason": null, "reconciledAt": "2026-10-19T14:33:14.390524+00:00", "repoId": "hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5645467", "taskType": "text-generation"}
{"batchId": "2f477057c7ec43eca67dacd9b9eb46d5", "completedAt": "2026-10-19T12:20:36.162545+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T11:58:25.852127+00:00", "framework": "vllm_tokenizer_patch", "intentId": "63ce37f826f14ede8c320b620a768f1d", "lastModified": "2026-10-16T15:13:58+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-7B-MLX-4bit", "reason": null, "reconciledAt": "2026-10-19T14:33:14.391189+00:00", "repoId": "IFM/Jais-3-7B-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5651876", "taskType": "text-generation"} {"batchId": "2f477057c7ec43eca67dacd9b9eb46d5", "completedAt": "2026-10-19T12:20:36.162545+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T11:58:25.852127+00:00", "framework": "vllm_tokenizer_patch", "intentId": "63ce37f826f14ede8c320b620a768f1d", "lastModified": "2026-10-16T15:13:58+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-7B-MLX-4bit", "reason": null, "reconciledAt": "2026-10-19T14:33:14.391189+00:00", "repoId": "IFM/Jais-3-7B-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5651876", "taskType": "text-generation"}
{"batchId": "2307b4d26c774fefb0e77ebb65885ddb", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:44:16.146356+00:00", "framework": "vllm_tokenizer_patch", "intentId": "38b342f5f3c54cae93e51088d984a885", "lastModified": "2026-10-19T08:34:36+00:00", "modelAddress": "https://modelscope.cn/models/XingChen-AGI/Xing4.0-29B-Intent-FP8", "repoId": "XingChen-AGI/Xing4.0-29B-Intent-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "2307b4d26c774fefb0e77ebb65885ddb", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:44:16.146463+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8bb3922c4449445687ce497dda30a3f1", "lastModified": "2026-10-15T14:37:21+00:00", "modelAddress": "https://modelscope.cn/models/IFM/K2-Horizon-32B-FP8", "repoId": "IFM/K2-Horizon-32B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "2307b4d26c774fefb0e77ebb65885ddb", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:44:16.146512+00:00", "framework": "vllm_tokenizer_patch", "intentId": "57d5d8b3c37742f6b2b59e6a9ef9ac5c", "lastModified": "2026-10-15T18:35:13+00:00", "modelAddress": "https://modelscope.cn/models/rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit", "repoId": "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "2307b4d26c774fefb0e77ebb65885ddb", "configFingerprint": "1feca051d54bd5fe5f2c2478646d6db59f6f200ee2e0327978b06c26f1d8ed2a", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:44:16.146556+00:00", "framework": "llamacpp", "intentId": "5c5e17d75e8043808c522cd2aa1522f9", "lastModified": "2026-10-15T23:18:06+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/microsoft-UserRepGen-4B-GGUF", "repoId": "prithivMLmods/microsoft-UserRepGen-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "2307b4d26c774fefb0e77ebb65885ddb", "configFingerprint": "e9c4f4f15802a39a57c6e07956c53755f75fc438be43d1164a8a2eda32456b1e", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:44:16.146614+00:00", "framework": "llamacpp", "intentId": "3db60c6725e84be58b772058caea4a8d", "lastModified": "2026-10-18T14:39:44+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "repoId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "2307b4d26c774fefb0e77ebb65885ddb", "configFingerprint": "02e187e3671a31235c75c7c9ad7c52e86e0476bdc3118ddf379ddb46a07261d1", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:44:16.146674+00:00", "framework": "llamacpp", "intentId": "04bdb88e9a794d90b29cba2c539a844a", "lastModified": "2026-10-19T05:18:16+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf", "repoId": "OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "2307b4d26c774fefb0e77ebb65885ddb", "configFingerprint": "a7a7d00616db408ae5c0df2a7cb156b93da7e857ba3eeb80a28825bbcf98f013", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:44:16.146731+00:00", "framework": "llamacpp", "intentId": "c9d03a0c9ae44f08b433ea3d6e21b82f", "lastModified": "2026-10-18T14:13:55+00:00", "modelAddress": "https://modelscope.cn/models/castorini/gaggle-nanochat-pretrained-climbmix-20260924", "repoId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "2307b4d26c774fefb0e77ebb65885ddb", "configFingerprint": "fc78709d4e85c217c994d6286e817ec9d9eae27c62f744569fd17a8b92fdf5ec", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:44:16.146789+00:00", "framework": "llamacpp", "intentId": "1915a0a8759a4af29f6fba750705f3de", "lastModified": "2026-10-19T06:51:21+00:00", "modelAddress": "https://modelscope.cn/models/bartowski/OpenPathAI_Orbit-3.2-Nano-GGUF", "repoId": "bartowski/OpenPathAI_Orbit-3.2-Nano-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "2307b4d26c774fefb0e77ebb65885ddb", "configFingerprint": "61898f295f143f06988745beef05f856402c5162f007122829060f3694145199", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:44:16.146845+00:00", "framework": "llamacpp", "intentId": "fbc4ad61a36d4a218acbcc6be677f142", "lastModified": "2026-10-15T14:56:28+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF", "repoId": "DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "2307b4d26c774fefb0e77ebb65885ddb", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:44:16.146899+00:00", "framework": "llamacpp", "intentId": "8604523f8da14915a4f0061c09917419", "lastModified": "2026-10-19T05:18:14+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "repoId": "OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "2307b4d26c774fefb0e77ebb65885ddb", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:44:16.146950+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2c92f722753848c0a804ed3927d32d39", "lastModified": "2026-10-19T07:00:41+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-8B-W8A8", "repoId": "iluvatar-corex/Qwen3-8B-W8A8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "2307b4d26c774fefb0e77ebb65885ddb", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:44:16.147003+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5e6b069d7fde421abe4640d33a7a94ea", "lastModified": "2026-10-19T07:29:23+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-14B-W8A8", "repoId": "iluvatar-corex/Qwen3-14B-W8A8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "completedAt": "2026-10-19T14:33:00.092115+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389969+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b5439a281070481090d75135d42a682c", "repoId": "DavidAU/LFM2-8B-A1B-SpeedDemon-The-Deckard-II-Series-A", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} {"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "completedAt": "2026-10-19T14:33:00.092115+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389969+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b5439a281070481090d75135d42a682c", "repoId": "DavidAU/LFM2-8B-A1B-SpeedDemon-The-Deckard-II-Series-A", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "completedAt": "2026-10-19T14:33:00.092112+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389926+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cb45c40d7b344793b7b9ce623209313d", "repoId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} {"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "completedAt": "2026-10-19T14:33:00.092112+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389926+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cb45c40d7b344793b7b9ce623209313d", "repoId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "completedAt": "2026-10-19T14:33:00.092109+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389884+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6807bff875104fe79d51acc252a53f03", "repoId": "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} {"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "completedAt": "2026-10-19T14:33:00.092109+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389884+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6807bff875104fe79d51acc252a53f03", "repoId": "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "651df4da42bcd688cd9277b6812bbf0aa41f15249c2cf1d6bda229985e2e69c4", ".modelhub_state/account_capacity.json": "651df4da42bcd688cd9277b6812bbf0aa41f15249c2cf1d6bda229985e2e69c4",
".modelhub_state/architecture_compatibility_blacklist.json": "8f1169717d7ec2fb6411c484bc678b70fa4635b00a69a3ba666cd04cdb0bb6ae", ".modelhub_state/architecture_compatibility_blacklist.json": "f77d44f8b545c1420f7f011ade38d39f1682ece3f55a457f5a28348410b93fa8",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "aa77f90fe62d71ed9bc569dcd2e00bbac175a59a84c5b29d274f411b79800886", ".modelhub_state/market_intelligence.json": "28f58534b935b0701f2207217e1a82fae0dc080bf8041bb080abd80f114fdbf8",
".modelhub_state/official_capabilities.json": "d218a00a81d6cecc3addd1873583c6fef557a796da5f89895669ef21f182191b", ".modelhub_state/official_capabilities.json": "e0b29ed19f9150471135e2aa5dcf64a93bb9d611c6addaa162d6479ae4a278df",
".modelhub_state/outcome_checkpoint.json": "2ea5336a6942ca1e9a269cef779ac12a30cfc6d9d259cd98b47bfc8eaf2fda9c", ".modelhub_state/outcome_checkpoint.json": "9984cd8adb371a2f076c3b8f18abaa21572ad053f4b85d3df1db65ac4d9d81cc",
".modelhub_state/queue_cleanup_latest.json": "27074b03987fc2f279ccc84565fc56c4236022f976c6479d04423ecbfa20e4de", ".modelhub_state/queue_cleanup_latest.json": "27074b03987fc2f279ccc84565fc56c4236022f976c6479d04423ecbfa20e4de",
".modelhub_state/recent_outcomes.jsonl": "fa91981c7ed2f069f9d64d025e5739016eda9d52a36ec06064f667e592ce0db4", ".modelhub_state/recent_outcomes.jsonl": "fa91981c7ed2f069f9d64d025e5739016eda9d52a36ec06064f667e592ce0db4",
".modelhub_state/recovery_active_tasks.jsonl": "396bd7f684afd802b1d1ada3eac22361033cdde88fd1d9d6de0472634e5aabaa", ".modelhub_state/recovery_active_tasks.jsonl": "396bd7f684afd802b1d1ada3eac22361033cdde88fd1d9d6de0472634e5aabaa",
".modelhub_state/recovery_intents.jsonl": "dccfb1330eaf5fff3ca769cb9ec67ef440c929197bba46027c0bacc1b50f3ad2", ".modelhub_state/recovery_intents.jsonl": "26e27246637573fbc4e3c11e86f287d8e5d08f16f83568ee8b9cb639e8d11347",
".modelhub_state/routing_intelligence.json": "ca603a8069885a55ae17ac9c10e3008a1afa63274bab55f1cf5cbd9ac3599e0f", ".modelhub_state/routing_intelligence.json": "ca603a8069885a55ae17ac9c10e3008a1afa63274bab55f1cf5cbd9ac3599e0f",
".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b", ".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b",
".modelhub_state/worker_crashes.jsonl": "75c8a6c5605f99dfe3e7d27ff6e9c6d730e1ee3a5016c812ed5cc3137a98684c", ".modelhub_state/worker_crashes.jsonl": "75c8a6c5605f99dfe3e7d27ff6e9c6d730e1ee3a5016c812ed5cc3137a98684c",
"ledger/submissions.jsonl": "f9f6c9fa1bdf4c14a79dbe51d9d5d82dd18a5417fd2d628955e55aa5f9690b0b", "ledger/submissions.jsonl": "f9f6c9fa1bdf4c14a79dbe51d9d5d82dd18a5417fd2d628955e55aa5f9690b0b",
"outcomes/submissions.jsonl": "8437abae3a3bd33d76e83302a7b811ecbaf6ff96f48221aa0073abe92d687758" "outcomes/submissions.jsonl": "df27a2a8d24e0ff55aa15210fc61916d24a75a4eed91c3cab7b742b78a8c1947"
}, },
"generation": 25829, "generation": 25830,
"phase": "cycle", "phase": "intent",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-19T14:33:14.645074+00:00", "updatedAt": "2026-10-19T14:44:16.314696+00:00",
"writerId": "eca444bc9fdf4bc89c9cfc2f8a9a6ac1" "writerId": "eca444bc9fdf4bc89c9cfc2f8a9a6ac1"
} }

2
outcomes/submissions.jsonl
View File

@@ -103,7 +103,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647505+00:00", "modelId": "JANGQ-AI/MiniMax-M2.7-JANGTQ", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60671749474, "estimatedRequiredGiB": 67.825, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 60688949222, "modelscopeLicense": "other", "modelscopeParams": 15303312058, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:jangtq-prestack", "custom_tag:minimax", "custom_tag:minimax-m2", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:2bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 60688949222}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.187054+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969030", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647505+00:00", "modelId": "JANGQ-AI/MiniMax-M2.7-JANGTQ", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60671749474, "estimatedRequiredGiB": 67.825, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 60688949222, "modelscopeLicense": "other", "modelscopeParams": 15303312058, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:jangtq-prestack", "custom_tag:minimax", "custom_tag:minimax-m2", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:2bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 60688949222}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.187054+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969030", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901659+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72670025872, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679340864, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int88", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679340864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.788367+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970568", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901659+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72670025872, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679340864, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int88", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679340864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.788367+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970568", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:46:14.462938+00:00", "modelId": "empero-ai/Qwen3.8-35B-A3B-Distill", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903778536, "estimatedRequiredGiB": 80.392, "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": 71933964484, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.6", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:moe", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-15T22:59:41.110897+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": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 71933964484}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:42:19.067096+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970926", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:46:14.462938+00:00", "modelId": "empero-ai/Qwen3.8-35B-A3B-Distill", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903778536, "estimatedRequiredGiB": 80.392, "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": 71933964484, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.6", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:moe", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-15T22:59:41.110897+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": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 71933964484}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:42:19.067096+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970926", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.191942+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.487823+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981859", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192060+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.441456+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981851", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192060+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.441456+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981851", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192031+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "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": 16313701503, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.502255+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981861", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192031+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "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": 16313701503, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.502255+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981861", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191915+00:00", "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29540133904, "estimatedRequiredGiB": 33.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 29547221374, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14770033664, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:Code", "custom_tag:Math", "custom_tag:Reasoning", "custom_tag:text-generation-inference", "custom_tag:Reinforcement-learning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29547221374}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.453969+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981852", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191915+00:00", "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29540133904, "estimatedRequiredGiB": 33.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 29547221374, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14770033664, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:Code", "custom_tag:Math", "custom_tag:Reasoning", "custom_tag:text-generation-inference", "custom_tag:Reinforcement-learning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29547221374}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.453969+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981852", "taskType": "text-generation", "verifyResult": null}
@@ -170,7 +169,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T21:31:27.760080+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "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": 2135575312, "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": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T13:27:47.747400+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5019633", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T21:31:27.760080+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "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": 2135575312, "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": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T13:27:47.747400+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5019633", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T21:31:27.760103+00:00", "modelId": "empero-ai/Qwen3.8-9B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306305296, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19329225494, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "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": 19329225494}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T13:29:10.961499+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5019639", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T21:31:27.760103+00:00", "modelId": "empero-ai/Qwen3.8-9B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306305296, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19329225494, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "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": 19329225494}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T13:29:10.961499+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5019639", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T22:45:05.970820+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "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": 2112106349, "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": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T14:44:16.051430+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5020425", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T22:45:05.970820+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "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": 2112106349, "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": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T14:44:16.051430+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5020425", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-23T00:45:45.504745+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Balance", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29644061610, "estimatedRequiredGiB": 33.16, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 29671037772, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8030801776, "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", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29671037772}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T16:43:47.256113+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5021799", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-23T02:54:50.764789+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T18:54:21.887542+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5023400", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-23T02:54:50.764789+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T18:54:21.887542+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5023400", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-23T02:54:50.764828+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754192, "estimatedRequiredGiB": 2.299, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "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": 2057327077}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T18:54:21.889548+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5023397", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-23T02:54:50.764828+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754192, "estimatedRequiredGiB": 2.299, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "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": 2057327077}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T18:54:21.889548+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5023397", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-23T03:13:40.768275+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242688, "estimatedRequiredGiB": 2.291, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2049905101, "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": 2049905101}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T19:09:59.407570+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5023594", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-23T03:13:40.768275+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242688, "estimatedRequiredGiB": 2.291, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2049905101, "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": 2049905101}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T19:09:59.407570+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5023594", "taskType": "text-generation", "verifyResult": null}