state: generation 11736 (cycle)
This commit is contained in:
@@ -2850,7 +2850,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T20:43:08.759249+00:00",
|
||||
"generatedAt": "2026-09-21T20:44:38.537522+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 143,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-21T20:28:30.751463+00:00",
|
||||
"communityAttemptedAt": "2026-09-21T20:44:49.167992+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-21T20:28:30.751463+00:00",
|
||||
"communityUpdatedAt": "2026-09-21T20:44:49.167992+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-21T15:33:56.261808+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-21T20:40:48.520732+00:00",
|
||||
"generatedAt": "2026-09-21T20:44:49.167992+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-21T20:40:48.520732+00:00",
|
||||
"catalogUpdatedAt": "2026-09-21T20:44:49.167992+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-21T20:40:48.520732+00:00",
|
||||
"generatedAt": "2026-09-21T20:44:49.167992+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6840,6 +6840,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-21T20:40:48.520732+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-21T20:44:49.167992+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T20:43:08.684873+00:00",
|
||||
"lastSyncTime": "2026-09-21T20:43:08.365510+00:00",
|
||||
"generatedAt": "2026-09-21T20:44:38.461573+00:00",
|
||||
"lastSyncTime": "2026-09-21T20:44:38.157515+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2977,24 +2977,24 @@
|
||||
"decisionSuccessRate": 0.0625,
|
||||
"decisionTotal": 32,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 39,
|
||||
"ambiguous_runtime": 40,
|
||||
"context_length": 3,
|
||||
"framework_architecture_unsupported": 26,
|
||||
"memory_capacity": 1,
|
||||
"参数/模板问题": 8
|
||||
},
|
||||
"failureCount": 77,
|
||||
"failureRate": 0.9747,
|
||||
"failureCount": 78,
|
||||
"failureRate": 0.975,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0253,
|
||||
"successRate": 0.025,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 79,
|
||||
"unresolvedFailureCount": 47
|
||||
"total": 80,
|
||||
"unresolvedFailureCount": 48
|
||||
},
|
||||
"Ascend_910-b3|vllm|text-generation": {
|
||||
"attributableFailureCount": 68,
|
||||
@@ -4504,9 +4504,9 @@
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 18,
|
||||
"decisionFailureRate": 0.9474,
|
||||
"decisionSuccessRate": 0.0526,
|
||||
"decisionTotal": 19,
|
||||
"decisionFailureRate": 0.9,
|
||||
"decisionSuccessRate": 0.1,
|
||||
"decisionTotal": 20,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"backend_operator": 2,
|
||||
@@ -4515,16 +4515,16 @@
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 32,
|
||||
"failureRate": 0.9697,
|
||||
"failureRate": 0.9412,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0303,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0588,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 33,
|
||||
"total": 34,
|
||||
"unresolvedFailureCount": 14
|
||||
},
|
||||
"Kunlunxin_p-800|vllm|text-generation": {
|
||||
@@ -5653,11 +5653,11 @@
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 78,
|
||||
"decisionFailureRate": 0.963,
|
||||
"decisionSuccessRate": 0.037,
|
||||
"decisionTotal": 81,
|
||||
"decisionFailureRate": 0.9512,
|
||||
"decisionSuccessRate": 0.0488,
|
||||
"decisionTotal": 82,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 88,
|
||||
"ambiguous_runtime": 89,
|
||||
"backend_operator": 2,
|
||||
"context_length": 3,
|
||||
"framework_architecture_unsupported": 66,
|
||||
@@ -5668,18 +5668,18 @@
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 27
|
||||
},
|
||||
"failureCount": 194,
|
||||
"failureRate": 0.9848,
|
||||
"failureCount": 195,
|
||||
"failureRate": 0.9799,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0152,
|
||||
"total": 197,
|
||||
"unresolvedFailureCount": 115
|
||||
"successCount": 4,
|
||||
"successRate": 0.0201,
|
||||
"total": 199,
|
||||
"unresolvedFailureCount": 116
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T20:43:08.673957+00:00",
|
||||
"generatedAt": "2026-09-21T20:44:38.450744+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 99,
|
||||
@@ -5687,7 +5687,7 @@
|
||||
"decisionSuccessRate": 0.161,
|
||||
"decisionTotal": 118,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 100,
|
||||
"ambiguous_runtime": 101,
|
||||
"context_length": 3,
|
||||
"framework_architecture_unsupported": 91,
|
||||
"memory_capacity": 2,
|
||||
@@ -5697,15 +5697,15 @@
|
||||
"日志缺失": 3,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 268,
|
||||
"failureRate": 0.9338,
|
||||
"failureCount": 269,
|
||||
"failureRate": 0.934,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 19,
|
||||
"successRate": 0.0662,
|
||||
"total": 287,
|
||||
"unresolvedFailureCount": 169
|
||||
"successRate": 0.066,
|
||||
"total": 288,
|
||||
"unresolvedFailureCount": 170
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 322,
|
||||
@@ -5905,9 +5905,9 @@
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"attributableFailureCount": 20,
|
||||
"decisionFailureRate": 0.9524,
|
||||
"decisionSuccessRate": 0.0476,
|
||||
"decisionTotal": 21,
|
||||
"decisionFailureRate": 0.9091,
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 188,
|
||||
"backend_operator": 2,
|
||||
@@ -5919,13 +5919,13 @@
|
||||
"验证失败": 23
|
||||
},
|
||||
"failureCount": 252,
|
||||
"failureRate": 0.996,
|
||||
"failureRate": 0.9921,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.004,
|
||||
"total": 253,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0079,
|
||||
"total": 254,
|
||||
"unresolvedFailureCount": 232
|
||||
},
|
||||
"Kunlunxin_r-200-8f": {
|
||||
@@ -6164,9 +6164,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3
|
||||
"ambiguous_runtime": 4
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "gemma2",
|
||||
@@ -6178,8 +6178,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma3|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -14819,7 +14819,7 @@
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
@@ -14829,11 +14829,11 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "awq",
|
||||
"successCount": 1,
|
||||
"successCount": 2,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
|
||||
@@ -21511,9 +21511,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
@@ -21526,8 +21526,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -34262,6 +34262,28 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|awq|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "awq",
|
||||
"successCount": 1,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|35": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -38188,15 +38210,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16411,
|
||||
"totalRecords": 16605,
|
||||
"terminalRecords": 16413,
|
||||
"totalRecords": 16607,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5919,
|
||||
"decisionFailureRate": 0.8621,
|
||||
"decisionSuccessRate": 0.1379,
|
||||
"decisionTotal": 6866,
|
||||
"decisionFailureRate": 0.8619,
|
||||
"decisionSuccessRate": 0.1381,
|
||||
"decisionTotal": 6867,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4036,
|
||||
"ambiguous_runtime": 4037,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 105,
|
||||
@@ -38212,31 +38234,31 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 674
|
||||
},
|
||||
"failureCount": 15464,
|
||||
"failureRate": 0.9423,
|
||||
"failureCount": 15465,
|
||||
"failureRate": 0.9422,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 925,
|
||||
"successCount": 947,
|
||||
"successRate": 0.0577,
|
||||
"total": 16411,
|
||||
"unresolvedFailureCount": 8620
|
||||
"successCount": 948,
|
||||
"successRate": 0.0578,
|
||||
"total": 16413,
|
||||
"unresolvedFailureCount": 8621
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 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 MetaX_c-500 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-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-b3 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 Cambricon_mlu-370-x4 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 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。",
|
||||
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Sunrise_pt-200-x1|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。",
|
||||
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -38276,6 +38298,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16605,
|
||||
"summarizedRecords": 16607,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -548,7 +548,6 @@
|
||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "modelId": "inceptionai/Jais-2-8B-Chat", "submitTime": "2026-09-20T08:49:13.744928+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974217", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
|
||||
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "modelId": "neuralmagic/starcoder2-15b-FP8", "submitTime": "2026-09-20T08:49:13.737560+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974216", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
|
||||
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "submitTime": "2026-09-20T08:50:08.794809+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974249", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
|
||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-7B-Instruct-v0.3-quantized.w8a8", "modelId": "RedHatAI/Mistral-7B-Instruct-v0.3-quantized.w8a8", "submitTime": "2026-09-20T08:56:16.600052+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4974353", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
|
||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "submitTime": "2026-09-20T09:01:08.067421+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974395", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
|
||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "modelId": "RedHatAI/starcoder2-15b-FP8", "submitTime": "2026-09-20T09:01:08.068967+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974396", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
|
||||
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "submitTime": "2026-09-20T09:25:37.085364+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4976382", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
|
||||
|
||||
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.20.2",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "51ec053a5dd10c2ee385dac2802e0f1bf4fe1c9beccfce49a917a52daaa977c5",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "ed53105a4dc8b5d1970cdbdc3d595dbf158d6aeb01b9250edceffaf9fb7b13dc",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "1a658f7428d86fb8f29e55a8e9cc92e49975d40c1b2bc05cffc8100a9158761a",
|
||||
".modelhub_state/official_capabilities.json": "cadbd7b37975132efe92de70d3b6bc32866e86a74e0968014fe8563e2e96f122",
|
||||
".modelhub_state/outcome_checkpoint.json": "294e5641e8c3e84575adff0bb40870e91edc2047d3614fa0ff57d88c8d84ad99",
|
||||
".modelhub_state/market_intelligence.json": "d0b96d9d15f561cff0788bbb31ebc35c33331d35acd98ee5dfe846d53042ac58",
|
||||
".modelhub_state/official_capabilities.json": "82aa4819d3fd961f61a4cbb46d4feb871885ace8519afe09f31c217e570555f0",
|
||||
".modelhub_state/outcome_checkpoint.json": "41bd775e57f7e2eff2e564bf85f7b54bd286c0f6639073d8edc63f57b31c5f86",
|
||||
".modelhub_state/queue_cleanup_latest.json": "f93bde2de8f7cc7073f34b5456a3df43c8f54023eacfce210dc11e227efd469c",
|
||||
".modelhub_state/recent_outcomes.jsonl": "3322c0aff3c2626e7202c517cadb9eeb963fcd0ef037950fdcef95d9132e8f01",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "6a2657f0305a7528c5a27fe4bde30175562a6b4a4fbe206c50318bc1804144bb",
|
||||
".modelhub_state/recovery_intents.jsonl": "fc6501b025d46c411cc15587621c551d4e24e71d6a59507f1a849715275c26b7",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "2af2351d5c8eb57c11cf47a621af01f5538746568774bbde95edddff24a03f85",
|
||||
".modelhub_state/recovery_intents.jsonl": "bd10943cba10b08066ad8b2ce147a16228716cfc2d7acc044c3202a0a5b8599c",
|
||||
".modelhub_state/routing_intelligence.json": "878705d3b8037cda27b1ec882a6200aa4d7b0f067862c3e66f9584e8badc8f42",
|
||||
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
|
||||
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
|
||||
"ledger/submissions.jsonl": "ab92f5e5bbc2f525b92a6ba9daf927b8b7e8dc779990fe578fea3a0f302c1ac8",
|
||||
"outcomes/submissions.jsonl": "d93e0cbe935b70a1ec7b13514622af8d003a405ebe60c0a8a0a8a11d1c832a34"
|
||||
"ledger/submissions.jsonl": "1cbe6034a4128fe385c5bcd26ec68de06faddf7a5a2882091c1e66bff5fb9c3e",
|
||||
"outcomes/submissions.jsonl": "73c1734577e70b3b6bedb9339b037491bdd714e3dc8bfb77b6cd5172daf07926"
|
||||
},
|
||||
"generation": 11735,
|
||||
"phase": "cycle_no_slots",
|
||||
"generation": 11736,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-21T20:43:24.364605+00:00",
|
||||
"updatedAt": "2026-09-21T20:45:00.622372+00:00",
|
||||
"writerId": "8b35139af6674067a339a670222d4b67"
|
||||
}
|
||||
|
||||
@@ -455,7 +455,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599690+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T03:30:31.146899+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969812", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:01:00.671231+00:00", "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325202, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325202}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.351352+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969964", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:01:00.670537+00:00", "modelId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720442075, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8720442075}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.293456+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969956", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.670617+00:00", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.347716+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969963", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.670531+00:00", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236742}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.349301+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969958", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.670786+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299781, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299781}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.357907+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969965", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.670714+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673720, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860673720}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.343922+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969961", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -500,7 +499,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671063+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "e4f10af7e21b1a730b2dfa32856745ab0e7a14867778026d61065fda3de90727", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008118474, "modelscopeLicense": "cc-by-nc-sa-4.0", "modelscopeParams": 7501651968, "modelscopeTags": ["license:cc-by-nc-sa-4.0", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008118474}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.739370+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970046", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.670485+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426233716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426233716}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:46:29.638998+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970108", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.671117+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:46:29.642501+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970106", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.670906+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:46:29.583837+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970114", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.671197+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:46:29.640961+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970105", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.670681+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:46:29.646657+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970109", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.670754+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:46:29.645217+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970116", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user