state: generation 8208 (cycle)
This commit is contained in:
@@ -1693,7 +1693,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-16T13:37:34.605832+00:00",
|
||||
"generatedAt": "2026-09-16T13:40:03.594699+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 82,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -75,7 +75,7 @@
|
||||
"7": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 599,
|
||||
"listingErrors": 600,
|
||||
"nextPage": 1,
|
||||
"recordsScanned": 0,
|
||||
"uniqueRecords": 0
|
||||
@@ -102,12 +102,12 @@
|
||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"failureLogsInspected": 0,
|
||||
"mode": "incremental_decision_only",
|
||||
"nextAccountIndex": 7,
|
||||
"nextAccountIndex": 8,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-16T13:37:34.576655+00:00",
|
||||
"updatedAt": "2026-09-16T13:40:03.568533+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-16T13:35:34.865604+00:00",
|
||||
"generatedAt": "2026-09-16T13:37:37.913459+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-16T13:02:19.711307+00:00",
|
||||
"lastSyncTime": "2026-09-16T13:02:17.413843+00:00",
|
||||
"generatedAt": "2026-09-16T13:37:37.865620+00:00",
|
||||
"lastSyncTime": "2026-09-16T13:37:37.810445+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2365,9 +2365,9 @@
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 58,
|
||||
"decisionFailureRate": 0.8788,
|
||||
"decisionSuccessRate": 0.1212,
|
||||
"decisionTotal": 66,
|
||||
"decisionFailureRate": 0.8657,
|
||||
"decisionSuccessRate": 0.1343,
|
||||
"decisionTotal": 67,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 11,
|
||||
"backend_operator": 27,
|
||||
@@ -2378,16 +2378,16 @@
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 78,
|
||||
"failureRate": 0.907,
|
||||
"failureRate": 0.8966,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 8,
|
||||
"successRate": 0.093,
|
||||
"successCount": 9,
|
||||
"successRate": 0.1034,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 86,
|
||||
"total": 87,
|
||||
"unresolvedFailureCount": 20
|
||||
},
|
||||
"Mthreads_s4000|llamacpp|text-generation": {
|
||||
@@ -2785,9 +2785,9 @@
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 359,
|
||||
"decisionFailureRate": 0.9625,
|
||||
"decisionSuccessRate": 0.0375,
|
||||
"decisionTotal": 373,
|
||||
"decisionFailureRate": 0.9599,
|
||||
"decisionSuccessRate": 0.0401,
|
||||
"decisionTotal": 374,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 222,
|
||||
"backend_operator": 35,
|
||||
@@ -2801,13 +2801,13 @@
|
||||
"参数/模板问题": 31
|
||||
},
|
||||
"failureCount": 614,
|
||||
"failureRate": 0.9777,
|
||||
"failureRate": 0.9762,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 14,
|
||||
"successRate": 0.0223,
|
||||
"total": 628,
|
||||
"successCount": 15,
|
||||
"successRate": 0.0238,
|
||||
"total": 629,
|
||||
"unresolvedFailureCount": 253
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2918,7 +2918,7 @@
|
||||
"unresolvedFailureCount": 5
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-16T13:02:19.705751+00:00",
|
||||
"generatedAt": "2026-09-16T13:37:37.857870+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 47,
|
||||
@@ -3131,9 +3131,9 @@
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 58,
|
||||
"decisionFailureRate": 0.7733,
|
||||
"decisionSuccessRate": 0.2267,
|
||||
"decisionTotal": 75,
|
||||
"decisionFailureRate": 0.7632,
|
||||
"decisionSuccessRate": 0.2368,
|
||||
"decisionTotal": 76,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 11,
|
||||
"backend_operator": 27,
|
||||
@@ -3145,13 +3145,13 @@
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 135,
|
||||
"failureRate": 0.8882,
|
||||
"failureRate": 0.8824,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 17,
|
||||
"successRate": 0.1118,
|
||||
"total": 152,
|
||||
"successCount": 18,
|
||||
"successRate": 0.1176,
|
||||
"total": 153,
|
||||
"unresolvedFailureCount": 77
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -5069,7 +5069,7 @@
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 4,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
@@ -5079,11 +5079,11 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "awq",
|
||||
"successCount": 4,
|
||||
"successCount": 5,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
|
||||
@@ -9425,7 +9425,7 @@
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 4,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
@@ -9436,11 +9436,11 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "awq",
|
||||
"successCount": 4,
|
||||
"successCount": 5,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|28": {
|
||||
@@ -10802,13 +10802,13 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 2012,
|
||||
"totalRecords": 2106,
|
||||
"terminalRecords": 2013,
|
||||
"totalRecords": 2107,
|
||||
"totals": {
|
||||
"attributableFailureCount": 643,
|
||||
"decisionFailureRate": 0.8918,
|
||||
"decisionSuccessRate": 0.1082,
|
||||
"decisionTotal": 721,
|
||||
"decisionFailureRate": 0.8906,
|
||||
"decisionSuccessRate": 0.1094,
|
||||
"decisionTotal": 722,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 491,
|
||||
"backend_operator": 45,
|
||||
@@ -10823,13 +10823,13 @@
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1934,
|
||||
"failureRate": 0.9612,
|
||||
"failureRate": 0.9608,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 10,
|
||||
"successCount": 78,
|
||||
"successRate": 0.0388,
|
||||
"total": 2012,
|
||||
"successCount": 79,
|
||||
"successRate": 0.0392,
|
||||
"total": 2013,
|
||||
"unresolvedFailureCount": 1281
|
||||
},
|
||||
"warnings": [
|
||||
@@ -10837,14 +10837,14 @@
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -10869,6 +10869,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 2106,
|
||||
"summarizedRecords": 2107,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "2fb0fb3349f74bd64ae1fadfa127def25ab8978cd6d14128e43a0a6e9ecfec0b",
|
||||
".modelhub_state/architecture_history_backfill.json": "b07159224b3cf76c6118fcd6da0e79971f8fcf1ac7058ba54813f579cc591a6f",
|
||||
".modelhub_state/market_intelligence.json": "d17d1fe6b480095bb132ef8ddc0fd7996e9175ff7fd649a12a979317898b5e24",
|
||||
".modelhub_state/official_capabilities.json": "c2fbcf84ea5c7157c4782e60dce4801f21ee85eddac0f32800bfdb4486ebf5eb",
|
||||
".modelhub_state/outcome_checkpoint.json": "4c01e816843e9c64d380a6a0511dce159ae0d6b3fac957d594ade78c073131fa",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "382a48bb0d17bf06069a556e8e762a306ddb7a144433f4d2fd9ea67d91418416",
|
||||
".modelhub_state/architecture_history_backfill.json": "5abd75b325cd3e3787f075e26d2b794f9f695ab913065d297a89e46b2b58fa9c",
|
||||
".modelhub_state/market_intelligence.json": "56b10917dfaba2ec03aba5951914a8875edbedaa1c4fc750a6058f308a981b9a",
|
||||
".modelhub_state/official_capabilities.json": "695d750fd6def21463f9e165824c3610488651e6ca3a75d4cdc675e9e04a3b27",
|
||||
".modelhub_state/outcome_checkpoint.json": "9cb6d521360f1511cd52b7279960667c17f6221c813838266f95372315055fa9",
|
||||
".modelhub_state/queue_cleanup_latest.json": "dee9467fbfd9b1941e02aab40f46f40feb7e889b1387e997a8c65cdf65c2d707",
|
||||
".modelhub_state/recent_outcomes.jsonl": "52d3c74c52faf027c74ed17f0bc5f7b42fef66462005416e3195190563b56597",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "6f35044aef5cdc02c576bcecc615dc476bcc5b47745e709555381b23f79736f7",
|
||||
".modelhub_state/recovery_intents.jsonl": "c62af754277fe8e9ea57744d73527814010efb177746176c39bd4b7adf75e42b",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "140ee2063b38ddc69984d60656fb662490055ea6f8f238727587f9cc3fcb4c8f",
|
||||
".modelhub_state/recovery_intents.jsonl": "646b786a7153b35aef10a83be91eecedc5b284048809d7d8de453bdf9f1da278",
|
||||
".modelhub_state/routing_intelligence.json": "a15a1e96d6092b9e705a6949f76da6524eff005c54bfa5fbbfd90e336be261fb",
|
||||
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
|
||||
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
|
||||
"ledger/submissions.jsonl": "e6a1d4d5ab7c0f9d0fa9ed5f146060ba93f18fda6433cf7c9115fc85975f6040",
|
||||
"outcomes/submissions.jsonl": "da1566c72d08f6430c61e3e0a52911a981de209188fa335510243bedc1c1174a"
|
||||
"outcomes/submissions.jsonl": "6408e7d15b72bb3c1a40eeff7f90c28c391c8b3b76ebf04f2e2211245ae2d4d4"
|
||||
},
|
||||
"generation": 8207,
|
||||
"generation": 8208,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-16T13:37:35.168680+00:00",
|
||||
"updatedAt": "2026-09-16T13:40:04.392370+00:00",
|
||||
"writerId": "eccb3e0018f640d19e578c271a207b5c"
|
||||
}
|
||||
|
||||
@@ -24,7 +24,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T23:51:52.413124+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:49:37.968504+00:00", "targetGpu": "Biren_166m", "taskId": "4629573", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T00:08:56.210086+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "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": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:05:38.973026+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4629768", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T00:12:22.613750+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 44221632439, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:10:19.951781+00:00", "targetGpu": "MetaX_c-500", "taskId": "4629851", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T00:12:22.613744+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:10:19.953932+00:00", "targetGpu": "MetaX_c-500", "taskId": "4629853", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T00:55:08.690919+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9514532079, "estimatedRequiredGiB": 10.658, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-04T16:45:54.339948+00:00", "targetGpu": "Biren_166m", "taskId": "4630659", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T00:55:08.690909+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:50:16.092995+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4630839", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T00:58:33.712526+00:00", "modelId": "nm-testing/tinyllama-marlin24-w4a16-group128", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 640856992, "estimatedRequiredGiB": 0.718, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 642705637, "modelscopeLicense": null, "modelscopeParams": 259844096, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 642705637}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:55:10.211615+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4630908", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user