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

state: generation 19037 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-01 02:55:35 +00:00
parent a61d03d0b2
commit 2570abf057
9 changed files with 1488 additions and 1445 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -3341,7 +3341,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-01T02:43:30.048337+00:00",
"generatedAt": "2026-10-01T02:54:18.801291+00:00",
"summary": {
"activeBlockCount": 168,
"byGpuFramework": {

6
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-10-01T02:40:07.249462+00:00",
"communityAttemptedAt": "2026-10-01T02:55:20.742381+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-10-01T02:40:07.249462+00:00",
"communityUpdatedAt": "2026-10-01T02:55:20.742381+00:00",
"frameworkAttemptedAt": "2026-10-01T02:08:52.569292+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-01T02:52:17.762290+00:00",
"generatedAt": "2026-10-01T02:55:20.742381+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-10-01T02:52:17.762290+00:00",
"catalogUpdatedAt": "2026-10-01T02:55:20.742381+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-10-01T02:52:17.762290+00:00",
"generatedAt": "2026-10-01T02:55:20.742381+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6381,6 +6381,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-10-01T02:52:17.762290+00:00",
"taskTreeUpdatedAt": "2026-10-01T02:55:20.742381+00:00",
"version": 1
}

139
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-01T02:10:10.852127+00:00",
"lastSyncTime": "2026-10-01T02:10:10.543716+00:00",
"generatedAt": "2026-10-01T02:54:18.718305+00:00",
"lastSyncTime": "2026-10-01T02:54:18.466130+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -5008,10 +5008,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 149,
"ambiguous_runtime": 150,
"参数/模板问题": 3
},
"failureCount": 152,
"failureCount": 153,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -5021,8 +5021,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 152,
"unresolvedFailureCount": 152
"total": 153,
"unresolvedFailureCount": 153
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 61,
@@ -5862,19 +5862,19 @@
"unresolvedFailureCount": 72
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 57,
"attributableFailureCount": 58,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 57,
"decisionTotal": 58,
"failureBreakdown": {
"ambiguous_runtime": 42,
"framework_architecture_unsupported": 22,
"model_load": 11,
"model_load": 12,
"repository_structure": 5,
"runtime_memory": 19,
"参数/模板问题": 11
},
"failureCount": 110,
"failureCount": 111,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"pendingCount": 0,
@@ -5884,7 +5884,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 110,
"total": 111,
"unresolvedFailureCount": 53
},
"hygon_k100-ai|vllm|text-generation": {
@@ -6117,26 +6117,26 @@
"unresolvedFailureCount": 100
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 57,
"attributableFailureCount": 58,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 57,
"decisionTotal": 58,
"failureBreakdown": {
"ambiguous_runtime": 42,
"framework_architecture_unsupported": 22,
"model_load": 11,
"model_load": 12,
"repository_structure": 5,
"runtime_memory": 19,
"参数/模板问题": 11
},
"failureCount": 110,
"failureCount": 111,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 110,
"total": 111,
"unresolvedFailureCount": 53
},
"vllm_0_17_0_corex_4_4_0": {
@@ -6169,7 +6169,7 @@
"decisionSuccessRate": 0.0307,
"decisionTotal": 163,
"failureBreakdown": {
"ambiguous_runtime": 337,
"ambiguous_runtime": 338,
"backend_operator": 9,
"framework_architecture_unsupported": 38,
"memory_capacity": 10,
@@ -6178,15 +6178,15 @@
"tokenizer_compatibility": 92,
"参数/模板问题": 13
},
"failureCount": 530,
"failureCount": 531,
"failureRate": 0.9907,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 22,
"successCount": 5,
"successRate": 0.0093,
"total": 535,
"unresolvedFailureCount": 350
"total": 536,
"unresolvedFailureCount": 351
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 140,
@@ -6217,7 +6217,7 @@
"unresolvedFailureCount": 220
}
},
"generatedAt": "2026-10-01T02:10:10.836570+00:00",
"generatedAt": "2026-10-01T02:54:18.705539+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 111,
@@ -6449,7 +6449,7 @@
"decisionSuccessRate": 0.066,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 237,
"ambiguous_runtime": 238,
"backend_operator": 23,
"framework_architecture_unsupported": 37,
"memory_capacity": 3,
@@ -6462,15 +6462,15 @@
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 407,
"failureCount": 408,
"failureRate": 0.9831,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 7,
"successRate": 0.0169,
"total": 414,
"unresolvedFailureCount": 307
"total": 415,
"unresolvedFailureCount": 308
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -6610,10 +6610,10 @@
"unresolvedFailureCount": 1322
},
"hygon_k100-ai": {
"attributableFailureCount": 737,
"decisionFailureRate": 0.9534,
"decisionSuccessRate": 0.0466,
"decisionTotal": 773,
"attributableFailureCount": 738,
"decisionFailureRate": 0.9535,
"decisionSuccessRate": 0.0465,
"decisionTotal": 774,
"failureBreakdown": {
"ambiguous_runtime": 340,
"architecture_compatibility": 32,
@@ -6621,7 +6621,7 @@
"context_length": 46,
"framework_architecture_unsupported": 254,
"memory_capacity": 59,
"model_load": 71,
"model_load": 72,
"platform_infrastructure": 4,
"repository_structure": 121,
"runtime_memory": 74,
@@ -6630,14 +6630,14 @@
"日志缺失": 66,
"验证失败": 27
},
"failureCount": 1565,
"failureCount": 1566,
"failureRate": 0.9775,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 36,
"successRate": 0.0225,
"total": 1601,
"total": 1602,
"unresolvedFailureCount": 824
}
},
@@ -23307,6 +23307,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|torchao": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "torchao",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|stablelm|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -53450,6 +53473,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|torchao|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "torchao",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|stablelm|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -54025,22 +54072,22 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17180,
"totalRecords": 17401,
"terminalRecords": 17182,
"totalRecords": 17403,
"totals": {
"attributableFailureCount": 6159,
"attributableFailureCount": 6160,
"decisionFailureRate": 0.8633,
"decisionSuccessRate": 0.1367,
"decisionTotal": 7134,
"decisionTotal": 7135,
"failureBreakdown": {
"ambiguous_runtime": 4479,
"ambiguous_runtime": 4480,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 326,
"framework_architecture_unsupported": 2205,
"memory_capacity": 1206,
"model_load": 550,
"model_load": 551,
"platform_infrastructure": 944,
"repository_structure": 742,
"runtime_memory": 101,
@@ -54049,30 +54096,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16205,
"failureRate": 0.9432,
"failureCount": 16207,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 944,
"successCount": 975,
"successRate": 0.0568,
"total": 17180,
"unresolvedFailureCount": 9102
"successRate": 0.0567,
"total": 17182,
"unresolvedFailureCount": 9103
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Biren_166m 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 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 Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 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 MetaX_c-500 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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -54117,6 +54164,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17401,
"summarizedRecords": 17403,
"version": 1
}

1267
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1482
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

1
ledger/submissions.jsonl
View File

@@ -124,7 +124,6 @@
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-15T06:30:01.357590+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4867730", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B-INT8", "modelId": "hcnote/SparkMuse-4B-INT8", "submitTime": "2026-09-15T21:23:14.072183+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4880354", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-8B-A1B-preview", "modelId": "Edge0/Edge0-8B-A1B-preview", "submitTime": "2026-09-16T08:44:19.185430+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4889469", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-8B-A1B-preview", "modelId": "Edge0/Edge0-8B-A1B-preview", "submitTime": "2026-09-16T09:03:09.666793+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4889677", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-8B-A1B-preview", "modelId": "Edge0/Edge0-8B-A1B-preview", "submitTime": "2026-09-16T09:37:59.405066+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4890080", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-8B-A1B-preview", "modelId": "Edge0/Edge0-8B-A1B-preview", "submitTime": "2026-09-16T09:59:53.000301+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4890315", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-8B-A1B-preview", "modelId": "Edge0/Edge0-8B-A1B-preview", "submitTime": "2026-09-16T10:17:32.995862+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4890520", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}

20
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.22.1",
"checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "346d0c7095f155d522077fa7ac608218c009564addb7acb41ae3678c1246c644",
".modelhub_state/architecture_compatibility_blacklist.json": "5ba3776c189e26e5233a8905528da5af5ca0c4d26c2af46e7fc8a8b2cd441827",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "b46d0d3e40b37b3b3a97b3a05c0ee1111aec91a284052994fb7a19d5530b5f6b",
".modelhub_state/official_capabilities.json": "2100648feb1f5eeb15aa507e89871d3e63a1c4ecd1992839fcd71031cbe7778c",
".modelhub_state/outcome_checkpoint.json": "941b67058d42d107c5e07e5a9c28ae686c00b838f2a33c1aa07c194b0f385816",
".modelhub_state/market_intelligence.json": "21cf614882b1da6b0b36a0f74e2a72fd92bcf890a505b3373a72fdff55ac14ba",
".modelhub_state/official_capabilities.json": "99966e6ffbd2f74673c5967a3b8da5843962f865a2b9cfc46d0ac195c42d1c20",
".modelhub_state/outcome_checkpoint.json": "b87feb8bba31bc238148b700eca2b3226cbfb6807ddb6caae35a67f13d8fde67",
".modelhub_state/queue_cleanup_latest.json": "2ab9713b25b7d4ba561d3c77969513a372db37a9de30ef70151fb0193b2bc7ce",
".modelhub_state/recent_outcomes.jsonl": "73f23566b5b4b8c0176d6e15dac2ca91200b082f28f05f39862b89485e9e092d",
".modelhub_state/recovery_active_tasks.jsonl": "0c37d14e88f35caf73e36178589d0e53b4f6b8f1d0cceb709d3ea8b4d0882432",
".modelhub_state/recovery_intents.jsonl": "e18768a3218ed1405f085a2def712ac0f0be43fdd15036bab4ca4478b97ca933",
".modelhub_state/recovery_active_tasks.jsonl": "3a708902b562db3aba7cfe4e335d8c18ad3dfaefcd4ff80917c2f97889afb24f",
".modelhub_state/recovery_intents.jsonl": "322aeb59a0d1e616d3002abc8e6b0211707597d6ca455310ed4810d506022638",
".modelhub_state/routing_intelligence.json": "09cc69960b345ef40104091dc4737ddc82df87d637c93fb6b2c12b4e9f5ead9e",
".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c",
".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd",
"ledger/submissions.jsonl": "a2dc52e7c94ad3c129fce1c44650389165e52826ca460214ba7aedc22452a562",
"outcomes/submissions.jsonl": "891f5df050ccba91c6008910507f6b16b415a9bed44d7bb2b4a5ba361d0facf2"
"ledger/submissions.jsonl": "ac0cf722099f2eda29a035bd4f2090406738ec924a0305895c0e8dfaf5acbd5f",
"outcomes/submissions.jsonl": "02a97bec31b2c0dea3677d3300af47c0b0774b718a9318ee3ac209c27c7a2550"
},
"generation": 19036,
"generation": 19037,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-10-01T02:53:16.802632+00:00",
"updatedAt": "2026-10-01T02:55:35.619892+00:00",
"writerId": "a812d0e025c3474eb16b828a4d987334"
}

10
outcomes/submissions.jsonl
View File

@@ -128,7 +128,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-15T14:38:14.995834+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "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": 13269529926, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T06:30:01.357590+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4867730", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T22:59:41.110934+00:00", "modelId": "hcnote/SparkMuse-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4453695184, "estimatedRequiredGiB": 4.989, "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": 4463853848, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4114366080, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 4463853848}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T14:55:01.762871+00:00", "targetGpu": "MetaX_c-500", "taskId": "4874870", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T23:45:09.312003+00:00", "modelId": "hcnote/SparkMuse-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4453695184, "estimatedRequiredGiB": 4.989, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4463853848, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4114366080, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 4463853848}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T15:43:19.147650+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4875870", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-16T00:03:27.944069+00:00", "modelId": "hcnote/SparkMuse-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4453695184, "estimatedRequiredGiB": 4.989, "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": 4463853848, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4114366080, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 4463853848}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T16:00:25.150487+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4876202", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-16T05:28:53.501885+00:00", "modelId": "hcnote/SparkMuse-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4453695184, "estimatedRequiredGiB": 4.989, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4463853848, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4114366080, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 4463853848}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T21:23:14.072183+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4880354", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-16T06:24:42.305209+00:00", "modelId": "hcnote/SparkMuse-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4453695184, "estimatedRequiredGiB": 4.989, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4463853848, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4114366080, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 4463853848}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T22:23:03.683054+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4881077", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-16T07:23:50.803385+00:00", "modelId": "hcnote/SparkMuse-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4453695184, "estimatedRequiredGiB": 4.989, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4463853848, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4114366080, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 4463853848}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T23:23:24.114544+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4881705", "taskType": "text-generation", "verifyResult": null}
@@ -159,7 +158,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T17:21:23.552173+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "bb269a9a8b4c1eeb18e3ef78bedcf638c3d1821a581b2f17113cde2fcd8be6c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "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": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T09:19:02.317218+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4912678", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T17:42:14.260331+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7df61fc66119e362f4b324c308b44e18bd70c6e8415d3cf79ad822bc9e6377c3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "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": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T09:36:01.072109+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4912861", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T18:05:14.493617+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cde1dd013433575dd6e624ec4e742d4992d0b53d429ab95bc4dbe8884fc49e49", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T09:57:55.404929+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4913157", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-17T18:16:51.858886+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597699026, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597699026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T10:12:07.485492+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4913274", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-17T18:16:51.858895+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62431083040, "estimatedRequiredGiB": 69.776, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 62434089468, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 62434089468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T10:12:07.431503+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4913277", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-17T18:16:51.858917+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "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": 16320427112, "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:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T10:12:07.489740+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4913272", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-17T18:16:51.858863+00:00", "modelId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 52429250296, "estimatedRequiredGiB": 58.623, "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_text", "modelscopeFileSize": 52454809833, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26213016704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:expert-pruning", "custom_tag:code", "custom_tag:mtp", "custom_tag:ornith", "custom_tag:reap", "custom_tag:ream", "custom_tag:omnimergekit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 52454809833}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T10:12:07.491666+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4913273", "taskType": "text-generation", "verifyResult": null}
@@ -747,10 +745,10 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-30T14:58:16.546919+00:00", "modelId": "bytkim/Qwen3.8-27B-pi", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 59411825056, "estimatedRequiredGiB": 66.425, "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:speculative-decoding", "custom_tag:vision", "custom_tag:image", "custom_tag:multimodal", "custom_tag:image-text-to-text", "custom_tag:text-generation-inference", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:qwen38", "custom_tag:27b", "custom_tag:pi", "custom_tag:coding", "custom_tag:coder", "custom_tag:code-generation", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:reasoning", "custom_tag:conversational", "custom_tag:sft", "custom_tag:grpo", "custom_tag:reinforcement-learning", "custom_tag:bf16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 59435671311}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T06:48:36.947934+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5185957", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T01:47:36.964181+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T17:39:03.747924+00:00", "targetGpu": "MetaX_c-500", "taskId": "5199381", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T01:59:37.157091+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T17:56:22.153029+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5199635", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "1a33bafb1592ba879d75d40728c59b19045f022ef96602e20135e83970e9f13b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T18:43:37.345495+00:00", "targetGpu": "MetaX_c-500", "taskId": "5200238", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517272, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T18:43:37.348780+00:00", "targetGpu": "MetaX_c-500", "taskId": "5200237", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5067121544, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T18:43:37.346955+00:00", "targetGpu": "MetaX_c-500", "taskId": "5200239", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T18:43:37.247818+00:00", "targetGpu": "MetaX_c-500", "taskId": "5200236", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T02:54:18.466130+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "1a33bafb1592ba879d75d40728c59b19045f022ef96602e20135e83970e9f13b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T18:43:37.345495+00:00", "targetGpu": "MetaX_c-500", "taskId": "5200238", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T02:54:18.466070+00:00", "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517272, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T18:43:37.348780+00:00", "targetGpu": "MetaX_c-500", "taskId": "5200237", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T02:54:18.466091+00:00", "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5067121544, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T18:43:37.346955+00:00", "targetGpu": "MetaX_c-500", "taskId": "5200239", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T02:54:18.466100+00:00", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T18:43:37.247818+00:00", "targetGpu": "MetaX_c-500", "taskId": "5200236", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T19:00:16.876280+00:00", "targetGpu": "MetaX_c-500", "taskId": "5200515", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "645727a8c34425a2c3e191b5407d247f231e0d4e88f0bd3deb19333f39d09ba4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3892651456, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T19:00:30.049878+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5200516", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "8120661075bb80389dd6d7b11ccbb58a0586dc072989d5570471de11994360d9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2694119616, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T19:00:30.051413+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5200518", "taskType": "text-generation", "verifyResult": null}