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

state: generation 19244 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-01 13:49:50 +00:00
parent 8733a88567
commit ed187a000c
8 changed files with 1312 additions and 1266 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": "2026-10-01T13:37:44.819622+00:00",
"generatedAt": "2026-10-01T13:47:43.307453+00:00",
"summary": {
"activeBlockCount": 168,
"byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-01T13:46:40.557611+00:00",
"generatedAt": "2026-10-01T13:49:39.690021+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-10-01T13:46:40.557611+00:00",
"catalogUpdatedAt": "2026-10-01T13:49:39.690021+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-10-01T13:46:40.865376+00:00",
"generatedAt": "2026-10-01T13:49:39.690021+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6636,6 +6636,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-10-01T13:46:40.557611+00:00",
"taskTreeUpdatedAt": "2026-10-01T13:49:39.690021+00:00",
"version": 1
}

103
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-01T13:37:44.736731+00:00",
"lastSyncTime": "2026-10-01T13:37:44.450782+00:00",
"generatedAt": "2026-10-01T13:47:43.222376+00:00",
"lastSyncTime": "2026-10-01T13:47:42.951743+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3927,25 +3927,25 @@
"decisionSuccessRate": 0.3214,
"decisionTotal": 28,
"failureBreakdown": {
"ambiguous_runtime": 44,
"ambiguous_runtime": 45,
"framework_architecture_unsupported": 16,
"model_load": 3,
"platform_infrastructure": 1,
"参数/模板问题": 1,
"验证失败": 3
},
"failureCount": 68,
"failureRate": 0.8831,
"failureCount": 69,
"failureRate": 0.8846,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 9,
"successRate": 0.1169,
"successRate": 0.1154,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 77,
"unresolvedFailureCount": 48
"total": 78,
"unresolvedFailureCount": 49
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 25,
@@ -6098,7 +6098,7 @@
"decisionSuccessRate": 0.3929,
"decisionTotal": 56,
"failureBreakdown": {
"ambiguous_runtime": 94,
"ambiguous_runtime": 95,
"framework_architecture_unsupported": 28,
"model_load": 5,
"platform_infrastructure": 1,
@@ -6106,15 +6106,15 @@
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 136,
"failureRate": 0.8608,
"failureCount": 137,
"failureRate": 0.8616,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.1392,
"total": 158,
"unresolvedFailureCount": 101
"successRate": 0.1384,
"total": 159,
"unresolvedFailureCount": 102
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 59,
@@ -6217,7 +6217,7 @@
"unresolvedFailureCount": 225
}
},
"generatedAt": "2026-10-01T13:37:44.723981+00:00",
"generatedAt": "2026-10-01T13:47:43.209314+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 113,
@@ -6310,7 +6310,7 @@
"decisionSuccessRate": 0.0896,
"decisionTotal": 826,
"failureBreakdown": {
"ambiguous_runtime": 509,
"ambiguous_runtime": 510,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 305,
@@ -6323,15 +6323,15 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1619,
"failureCount": 1620,
"failureRate": 0.9563,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 74,
"successRate": 0.0437,
"total": 1693,
"unresolvedFailureCount": 851
"total": 1694,
"unresolvedFailureCount": 852
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 61,
@@ -11672,6 +11672,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|torchao": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "torchao",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|stablelm|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -35916,6 +35939,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|torchao|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "torchao",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|stablelm|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -54403,15 +54450,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17201,
"totalRecords": 17422,
"terminalRecords": 17202,
"totalRecords": 17423,
"totals": {
"attributableFailureCount": 6169,
"decisionFailureRate": 0.8635,
"decisionSuccessRate": 0.1365,
"decisionTotal": 7144,
"failureBreakdown": {
"ambiguous_runtime": 4490,
"ambiguous_runtime": 4491,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -54427,30 +54474,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16226,
"failureCount": 16227,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 944,
"successCount": 975,
"successRate": 0.0567,
"total": 17201,
"unresolvedFailureCount": 9113
"total": 17202,
"unresolvedFailureCount": 9114
},
"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。",
@@ -54495,6 +54542,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17422,
"summarizedRecords": 17423,
"version": 1
}

978
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1466
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

18
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": "415146ea22318a7d7a604f5062291ba105472fd9a8692aa57571f0313cc95035",
".modelhub_state/architecture_compatibility_blacklist.json": "1f68e7052624c18f94223f022998567f9c840781d65ee76a8454fb0443ffe7b3",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "cc413f2cc9a4c10852ec9ab98bd5b7c8c768ee7a023064335c3ba35871bb07d4",
".modelhub_state/official_capabilities.json": "9b975a30c01595870288b90cab59f88ff7d63d95ed4a39431f74dfa91142d6e1",
".modelhub_state/outcome_checkpoint.json": "ffcfb7c3d032199415753352dac670308c99323faa935f4b69703f1c38d6b555",
".modelhub_state/market_intelligence.json": "d746a712c971ea72a1f40e5c8424bbc3bb87788b98517be41e741624bca1c2bf",
".modelhub_state/official_capabilities.json": "b74dd93c331eca6d03652ae43bd676d2bb66e28927df0008b68e4c4199f49121",
".modelhub_state/outcome_checkpoint.json": "29709bc599df6c758e77a7985442c466a9321126d15dfeeb337840ebd7d0280d",
".modelhub_state/queue_cleanup_latest.json": "b8d4ee6abdce7b813a365a651d9af6115f89aed9cbf5ddf95e19efa44fc83b74",
".modelhub_state/recent_outcomes.jsonl": "2523ec2f7019354108df01107e7f0a74a17201a51201d3993b38b265a6fafd64",
".modelhub_state/recovery_active_tasks.jsonl": "a5f95fcc7dd0c7311865b3041518fa1209c65207a4f79da8a22f0bb8b831e0b9",
".modelhub_state/recovery_intents.jsonl": "5858b2f955ee70619f57dcc0ab8eef1b9b070a6e4822b8c9f3fd6f94f446b75d",
".modelhub_state/recovery_active_tasks.jsonl": "3170e0c5972adb1c35994c93fe4af6fe1ddeef0cfa640d46d99a3cf69101e857",
".modelhub_state/recovery_intents.jsonl": "35e494c939dc374119a25f120caec9ba6d0e7ff7fcfc07b740b2922ccfd1ca59",
".modelhub_state/routing_intelligence.json": "be70813f166dbb5be16db60ed04936b987ed15d3c008065b231ff723a2ff8af2",
".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c",
".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd",
"ledger/submissions.jsonl": "e2c74d18fabd2c6017616c383f1b540df8f1d0f5ae064de15fac75261b1098c9",
"outcomes/submissions.jsonl": "12c4bdf66b671cf92b4f3252386d8098906425f44b698c1674b718f5fbfd73b2"
"outcomes/submissions.jsonl": "a72ab37c7bca6d11767154a4bb5c82d7aa5535cb39723b8cb0b785584172861c"
},
"generation": 19243,
"generation": 19244,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-10-01T13:46:41.407973+00:00",
"updatedAt": "2026-10-01T13:49:50.701494+00:00",
"writerId": "a812d0e025c3474eb16b828a4d987334"
}

3
outcomes/submissions.jsonl
View File

@@ -125,7 +125,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-15T14:38:14.995814+00:00", "modelId": "mlx-community/Agents-A1-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": 13269529500, "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": 13269529500}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T06:30:01.355295+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4867726", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-15T14:38:14.995786+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "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": 20083974016, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "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": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T06:30:01.351500+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4867728", "taskType": "text-generation", "verifyResult": null}
{"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-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", "lastSyncTime": "2026-09-16T18:07:34.714203+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "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": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T09:59:53.000301+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4890315", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-16T18:24:50.147957+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "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": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T10:17:32.995862+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4890520", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-16T21:42:43.203686+00:00", "modelId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 52429250296, "estimatedRequiredGiB": 58.623, "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_text", "modelscopeFileSize": 52454809630, "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": "2026-09-16T13:37:27.004498+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4893449", "taskType": "text-generation", "verifyResult": null}
@@ -736,7 +735,7 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T03:00:54.465107+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-30T19:00:30.054397+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200517", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T03:00:54.465067+00:00", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-30T19:00:30.056861+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200519", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T03:19:50.448066+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "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": "waiting", "submitTime": "2026-09-30T19:16:58.857252+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200707", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T05:41:58.050597+00:00", "targetGpu": "MetaX_c-500", "taskId": "5208880", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T13:47:42.951714+00:00", "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T05:41:58.050597+00:00", "targetGpu": "MetaX_c-500", "taskId": "5208880", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T05:59:45.051636+00:00", "targetGpu": "MetaX_c-500", "taskId": "5209080", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T06:01:55.960786+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209103", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T06:17:59.744659+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209313", "taskType": "text-generation", "verifyResult": null}