state: generation 7650 (cycle)

This commit is contained in:
2026-09-15 11:02:13 +00:00
parent 93b65903ae
commit 34de5bd28a
10 changed files with 2045 additions and 2005 deletions

View File

@@ -1593,7 +1593,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-15T10:59:27.544879+00:00",
"generatedAt": "2026-09-15T11:02:13.065857+00:00",
"summary": {
"activeBlockCount": 78,
"byGpuFramework": {

View File

@@ -35,7 +35,7 @@
"2": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 556,
"listingErrors": 557,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 2,
"nextAccountIndex": 3,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-15T10:59:27.504951+00:00",
"updatedAt": "2026-09-15T11:02:13.040102+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-15T10:45:22.388293+00:00",
"communityAttemptedAt": "2026-09-15T11:00:37.485808+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-15T10:45:22.388293+00:00",
"communityUpdatedAt": "2026-09-15T11:00:37.485808+00:00",
"frameworkAttemptedAt": "2026-09-15T09:24:06.445335+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T10:57:36.429533+00:00",
"generatedAt": "2026-09-15T11:00:37.485808+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-15T10:50:55.915086+00:00",
"lastSyncTime": "2026-09-15T10:50:55.652660+00:00",
"generatedAt": "2026-09-15T11:00:28.671613+00:00",
"lastSyncTime": "2026-09-15T11:00:28.397814+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2310,21 +2310,21 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 38,
"attributableFailureCount": 39,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"decisionTotal": 39,
"failureBreakdown": {
"ambiguous_runtime": 42,
"backend_operator": 4,
"framework_architecture_unsupported": 28,
"framework_architecture_unsupported": 29,
"memory_capacity": 1,
"model_load": 2,
"repository_structure": 1,
"runtime_memory": 2,
"参数/模板问题": 3
},
"failureCount": 83,
"failureCount": 84,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2334,7 +2334,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 83,
"total": 84,
"unresolvedFailureCount": 45
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -2636,14 +2636,14 @@
"unresolvedFailureCount": 895
},
"vllm": {
"attributableFailureCount": 340,
"attributableFailureCount": 341,
"decisionFailureRate": 0.9827,
"decisionSuccessRate": 0.0173,
"decisionTotal": 346,
"decisionTotal": 347,
"failureBreakdown": {
"ambiguous_runtime": 218,
"backend_operator": 34,
"framework_architecture_unsupported": 251,
"framework_architecture_unsupported": 252,
"memory_capacity": 7,
"model_load": 27,
"platform_infrastructure": 2,
@@ -2652,14 +2652,14 @@
"tokenizer_compatibility": 7,
"参数/模板问题": 30
},
"failureCount": 590,
"failureCount": 591,
"failureRate": 0.9899,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 6,
"successRate": 0.0101,
"total": 596,
"total": 597,
"unresolvedFailureCount": 248
},
"vllm-mlu": {
@@ -2768,7 +2768,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-15T10:50:55.910730+00:00",
"generatedAt": "2026-09-15T11:00:28.666577+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 40,
@@ -3005,14 +3005,14 @@
"unresolvedFailureCount": 77
},
"Mthreads_s4000": {
"attributableFailureCount": 39,
"decisionFailureRate": 0.9512,
"decisionSuccessRate": 0.0488,
"decisionTotal": 41,
"attributableFailureCount": 40,
"decisionFailureRate": 0.9524,
"decisionSuccessRate": 0.0476,
"decisionTotal": 42,
"failureBreakdown": {
"ambiguous_runtime": 42,
"backend_operator": 4,
"framework_architecture_unsupported": 28,
"framework_architecture_unsupported": 29,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 1,
@@ -3020,14 +3020,14 @@
"参数/模板问题": 10,
"验证失败": 26
},
"failureCount": 117,
"failureRate": 0.9832,
"failureCount": 118,
"failureRate": 0.9833,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0168,
"total": 119,
"successRate": 0.0167,
"total": 120,
"unresolvedFailureCount": 78
},
"Sunrise_pt-200-x1": {
@@ -4977,6 +4977,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|nanbeige|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "nanbeige",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_moe|modelopt": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -8867,6 +8890,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|nanbeige|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "nanbeige",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_moe|modelopt|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -9372,17 +9419,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1916,
"totalRecords": 2010,
"terminalRecords": 1917,
"totalRecords": 2011,
"totals": {
"attributableFailureCount": 593,
"decisionFailureRate": 0.8985,
"decisionSuccessRate": 0.1015,
"decisionTotal": 660,
"attributableFailureCount": 594,
"decisionFailureRate": 0.8986,
"decisionSuccessRate": 0.1014,
"decisionTotal": 661,
"failureBreakdown": {
"ambiguous_runtime": 460,
"backend_operator": 44,
"framework_architecture_unsupported": 387,
"framework_architecture_unsupported": 388,
"memory_capacity": 12,
"model_load": 78,
"platform_infrastructure": 7,
@@ -9392,14 +9439,14 @@
"参数/模板问题": 116,
"验证失败": 673
},
"failureCount": 1849,
"failureCount": 1850,
"failureRate": 0.965,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 67,
"successRate": 0.035,
"total": 1916,
"total": 1917,
"unresolvedFailureCount": 1249
},
"warnings": [
@@ -9438,6 +9485,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2010,
"summarizedRecords": 2011,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -14,8 +14,6 @@
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T04:34:21.520300+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611267", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T04:34:21.518508+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611265", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/b77968543/Spark-X2.5-4B-Q8_0", "modelId": "b77968543/Spark-X2.5-4B-Q8_0", "submitTime": "2026-09-04T04:40:16.372199+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611339", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T04:51:18.804860+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4611484", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T04:51:18.805964+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4611483", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T05:06:37.162640+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611646", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T05:06:37.165709+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611648", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T05:06:37.161333+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611647", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
@@ -24,7 +22,6 @@
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "submitTime": "2026-09-04T07:12:30.054811+00:00", "targetGpu": "Biren_166m", "taskId": "4621809", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T07:40:37.506061+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4622172", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T07:56:50.952206+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4622417", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T08:10:58.159820+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622624", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T08:10:58.164553+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622621", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T08:14:12.544960+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4622655", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T08:33:06.846794+00:00", "targetGpu": "Biren_166m", "taskId": "4623002", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "65b934a8326cbb4939b863e80b724b6ee6df2c9a5bbb7d95f419ef91d6883d49",
".modelhub_state/architecture_history_backfill.json": "09d7e90ce15d395652af38212e9505ed3636b4e9e86afa089cba9236df93460a",
".modelhub_state/market_intelligence.json": "75d580f8869278a4bb0321708b01fe649b04d2cd296e5575c0b0f3cf9ea3992c",
".modelhub_state/official_capabilities.json": "80abd3d1c92de382c10349f9369221f335121b1c5b22d3cf019f816f102d5be4",
".modelhub_state/outcome_checkpoint.json": "1eb616028c9758c66745937195c3d43ae4736e833b38b758ea7152bc12738589",
".modelhub_state/architecture_compatibility_blacklist.json": "a86778e29c4d48f3de11f9921a6f82ac2126a47330af57397f4842580b4a831a",
".modelhub_state/architecture_history_backfill.json": "d46aa66103d6fbacd234baa99e08e8cf6ac5b01b9928738c47c411e9a110f3d7",
".modelhub_state/market_intelligence.json": "a29ada3c154278dc13e62d55d0b9bc8d4bcdc4cf193a92eaa2a812c72340e7e2",
".modelhub_state/official_capabilities.json": "dde8f1192e2785a5d2de9e14d3d0d2394ff799fbf9e3d89acd0a93f85f51a3c0",
".modelhub_state/outcome_checkpoint.json": "33808a3fc695d308c6a97a2f72f6f49e36e3e79ac7f4aeabb963a56d2a13f3ac",
".modelhub_state/queue_cleanup_latest.json": "3e511035a77fe68d9f1adfb35e149ee220beed7c3962d87b7d1892cc816fb69a",
".modelhub_state/recent_outcomes.jsonl": "f66316bd3b5e52cf73f6211e203829454b3a7409d4e47e1dd1ecc67d4e3f1d50",
".modelhub_state/recovery_active_tasks.jsonl": "7212b1a4d1160da7c5c1246b263686e96f6a227da91c2c4bf508da436643c488",
".modelhub_state/recovery_intents.jsonl": "6357bce61bcee6cb44062f0169403b6df11a094dbc89344efb56712058eab2af",
".modelhub_state/recovery_active_tasks.jsonl": "502a042ab596b5d2038a8997408879acb1e12436ba94f0e98af44c85e09ae324",
".modelhub_state/recovery_intents.jsonl": "13c2abd594b6d8252f36c7fdebcda7532bf072e6746022e734e78b86884d21e5",
".modelhub_state/routing_intelligence.json": "5c8070320d5755aaf914efa600b2d376703dd44fa4a64fb6e2078f23011d8cb3",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "84cdf5b3e615e2a34e6e49fe19a3ca9d12acf1f0e15d8a446e6f2acab93add59",
"outcomes/submissions.jsonl": "f1e64b3f4edb267833268a6800655e83ab445754fd47dd2aed3178b0cfa85b36"
"ledger/submissions.jsonl": "13fdcaaa093a350e18211faadff74ac2fe77d3b0636b1c71c071d0ace828b057",
"outcomes/submissions.jsonl": "ed3535f281e7a34ecdc0a31887e9f46cc250fcb4be80faebacda1151162c6c1f"
},
"generation": 7649,
"generation": 7650,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-15T10:59:27.699218+00:00",
"updatedAt": "2026-09-15T11:02:13.723021+00:00",
"writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c"
}

View File

@@ -74,7 +74,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:40:37.707812+00:00", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8dbcfce641caa83ec7080451f0410ae2c4732d92c35c6ea116cea836d3424ea2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2076674432, "estimatedRequiredGiB": 11.564, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10347343046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1942653248, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "custom_tag:edge", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10347343046}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:38:07.789820+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641229", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:57:50.112723+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "7fcefcc66e6b781d939ce31d9aa1c7a89bdfb773b9556e6dcde4e21754b1189f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4610579744, "estimatedRequiredGiB": 25.463, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 22784105135, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4326350848, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22784105135}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:56:19.745119+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641463", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397755+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:01.097550+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641563", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397684+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:09.008584+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641565", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397729+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:09.000926+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641564", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397749+00:00", "modelId": "LLM-Research/Phi-3.5-mini-instruct-bnb-4bit", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2264298476, "estimatedRequiredGiB": 2.533, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2266692143, "modelscopeLicense": "mit", "modelscopeParams": 3934684872, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:unsloth", "custom_tag:transformers", "custom_tag:phi3", "custom_tag:phi", "custom_tag:microsoft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "bitsandbytes", "repositoryOnDiskBytes": 2266692143}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:09.034612+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4641566", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142883+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9514532079, "estimatedRequiredGiB": 10.658, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9536343971, "modelscopeLicense": null, "modelscopeParams": 2519020032, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9536343971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.436989+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641789", "taskType": "text-generation", "verifyResult": null}