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

state: generation 17550 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-27 21:38:26 +00:00
parent 1c07ff2416
commit 8fd0a9c8ae
8 changed files with 1582 additions and 1584 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -3261,7 +3261,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-27T21:30:51.061116+00:00", "generatedAt": "2026-09-27T21:37:17.412838+00:00",
"summary": { "summary": {
"activeBlockCount": 164, "activeBlockCount": 164,
"byGpuFramework": { "byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -396,7 +396,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-27T21:36:15.176109+00:00", "generatedAt": "2026-09-27T21:38:22.961331+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{ {
"catalogUpdatedAt": "2026-09-27T21:36:15.176109+00:00", "catalogUpdatedAt": "2026-09-27T21:38:22.961331+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-09-27T21:36:15.176109+00:00", "generatedAt": "2026-09-27T21:38:22.961331+00:00",
"gpuCatalog": { "gpuCatalog": {
"Ascend_910-b3": { "Ascend_910-b3": {
"canVerify": true, "canVerify": true,
@@ -6575,6 +6575,6 @@
"updateTime": "2025-12-22 08:59:53" "updateTime": "2025-12-22 08:59:53"
} }
], ],
"taskTreeUpdatedAt": "2026-09-27T21:36:15.176109+00:00", "taskTreeUpdatedAt": "2026-09-27T21:38:22.961331+00:00",
"version": 1 "version": 1
} }

88
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-27T13:48:29.825492+00:00", "generatedAt": "2026-09-27T21:37:17.329347+00:00",
"lastSyncTime": "2026-09-27T13:48:29.557196+00:00", "lastSyncTime": "2026-09-27T21:37:17.059954+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -3871,12 +3871,12 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 24, "decisionTotal": 24,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 42, "ambiguous_runtime": 44,
"framework_architecture_unsupported": 23, "framework_architecture_unsupported": 23,
"memory_capacity": 1, "memory_capacity": 1,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 67, "failureCount": 69,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -3886,8 +3886,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 67, "total": 69,
"unresolvedFailureCount": 43 "unresolvedFailureCount": 45
}, },
"Cambricon_mlu-370-x8|unknown|feature_emb": { "Cambricon_mlu-370-x8|unknown|feature_emb": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -5962,7 +5962,7 @@
"decisionSuccessRate": 0.0261, "decisionSuccessRate": 0.0261,
"decisionTotal": 3720, "decisionTotal": 3720,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1582, "ambiguous_runtime": 1584,
"architecture_compatibility": 112, "architecture_compatibility": 112,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 93, "backend_operator": 93,
@@ -5976,15 +5976,15 @@
"tokenizer_compatibility": 416, "tokenizer_compatibility": 416,
"参数/模板问题": 50 "参数/模板问题": 50
}, },
"failureCount": 6126, "failureCount": 6128,
"failureRate": 0.9844, "failureRate": 0.9844,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 871, "platformFailureCount": 871,
"successCount": 97, "successCount": 97,
"successRate": 0.0156, "successRate": 0.0156,
"total": 6223, "total": 6225,
"unresolvedFailureCount": 1632 "unresolvedFailureCount": 1634
}, },
"vllm-customized": { "vllm-customized": {
"attributableFailureCount": 13, "attributableFailureCount": 13,
@@ -6134,7 +6134,7 @@
"unresolvedFailureCount": 197 "unresolvedFailureCount": 197
} }
}, },
"generatedAt": "2026-09-27T13:48:29.813327+00:00", "generatedAt": "2026-09-27T21:37:17.317408+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 102, "attributableFailureCount": 102,
@@ -6226,7 +6226,7 @@
"decisionSuccessRate": 0.0894, "decisionSuccessRate": 0.0894,
"decisionTotal": 817, "decisionTotal": 817,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 501, "ambiguous_runtime": 503,
"architecture_compatibility": 53, "architecture_compatibility": 53,
"context_length": 48, "context_length": 48,
"framework_architecture_unsupported": 297, "framework_architecture_unsupported": 297,
@@ -6239,15 +6239,15 @@
"日志缺失": 13, "日志缺失": 13,
"验证失败": 42 "验证失败": 42
}, },
"failureCount": 1603, "failureCount": 1605,
"failureRate": 0.9564, "failureRate": 0.9565,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 16, "platformFailureCount": 16,
"successCount": 73, "successCount": 73,
"successRate": 0.0436, "successRate": 0.0435,
"total": 1676, "total": 1678,
"unresolvedFailureCount": 843 "unresolvedFailureCount": 845
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"attributableFailureCount": 60, "attributableFailureCount": 60,
@@ -11320,9 +11320,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 5 "ambiguous_runtime": 6
}, },
"failureCount": 5, "failureCount": 6,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"modelType": "gemma2", "modelType": "gemma2",
@@ -11334,8 +11334,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 5, "total": 6,
"unresolvedFailureCount": 5 "unresolvedFailureCount": 6
}, },
"Cambricon_mlu-370-x4|vllm|text-generation|gemma2|none": { "Cambricon_mlu-370-x4|vllm|text-generation|gemma2|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -11803,9 +11803,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 10 "ambiguous_runtime": 11
}, },
"failureCount": 10, "failureCount": 11,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"modelType": "starcoder2", "modelType": "starcoder2",
@@ -11817,8 +11817,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 10, "total": 11,
"unresolvedFailureCount": 10 "unresolvedFailureCount": 11
}, },
"Cambricon_mlu-370-x8|vllm-customized|text-generation|aquila3|none": { "Cambricon_mlu-370-x8|vllm-customized|text-generation|aquila3|none": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -34054,9 +34054,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 2 "ambiguous_runtime": 3
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"loadSizeLog2Bucket": 32, "loadSizeLog2Bucket": 32,
@@ -34069,8 +34069,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 3
}, },
"Cambricon_mlu-370-x4|vllm|text-generation|gemma2|compressed-tensors|33": { "Cambricon_mlu-370-x4|vllm|text-generation|gemma2|compressed-tensors|33": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -34942,9 +34942,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 2 "ambiguous_runtime": 3
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"loadSizeLog2Bucket": 34, "loadSizeLog2Bucket": 34,
@@ -34957,8 +34957,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 3
}, },
"Cambricon_mlu-370-x8|vllm-customized|text-generation|aquila3|none|12": { "Cambricon_mlu-370-x8|vllm-customized|text-generation|aquila3|none|12": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -51385,15 +51385,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17063, "terminalRecords": 17065,
"totalRecords": 17284, "totalRecords": 17286,
"totals": { "totals": {
"attributableFailureCount": 6114, "attributableFailureCount": 6114,
"decisionFailureRate": 0.8636, "decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364, "decisionSuccessRate": 0.1364,
"decisionTotal": 7080, "decisionTotal": 7080,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4422, "ambiguous_runtime": 4424,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 128, "backend_operator": 128,
@@ -51409,15 +51409,15 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16097, "failureCount": 16099,
"failureRate": 0.9434, "failureRate": 0.9434,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 938, "platformFailureCount": 938,
"successCount": 966, "successCount": 966,
"successRate": 0.0566, "successRate": 0.0566,
"total": 17063, "total": 17065,
"unresolvedFailureCount": 9045 "unresolvedFailureCount": 9047
}, },
"warnings": [ "warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -51425,15 +51425,15 @@
"GPU Ascend_910-b4 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-x4 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 MetaX_c-500 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 Mthreads_s4000 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 Vastai_va16 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 Ascend_910-b3 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 Sunrise_pt-200-x1 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 Biren_166m 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 hygon_k100-ai 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 Iluvatar_bi-100 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 Kunlunxin_p-800 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 Iluvatar_bi-150 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。",
"组合 Ascend_910-b3|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。", "组合 Ascend_910-b3|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。",
"组合 Ascend_910-b3|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 Ascend_910-b3|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 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 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。",
@@ -51457,7 +51457,6 @@
"组合 Cambricon_mlu-370-x4|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 Cambricon_mlu-370-x4|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 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm-patch-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 hygon_k100-ai|vllm-patch-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 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。",
"组合 Iluvatar_mrv-100|unknown|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 Iluvatar_mrv-100|unknown|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 Mthreads_s4000|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 Mthreads_s4000|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 Iluvatar_bi-100|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 Iluvatar_bi-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51471,10 +51470,11 @@
"组合 Cambricon_mlu-370-x4|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 Cambricon_mlu-370-x4|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 Mthreads_s4000|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 Mthreads_s4000|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 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。", "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。",
"组合 Iluvatar_bi-150|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 Iluvatar_bi-150|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 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。"
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 17284, "summarizedRecords": 17286,
"version": 1 "version": 1
} }

1406
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1642
.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", "agentVersion": "2026.09.22.1",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "43945e75a0ea9543a28247b6eb784e4a649141569a960d3bd06ddcd9143e5976", ".modelhub_state/architecture_compatibility_blacklist.json": "4b53f1061901bc988cc1f2913894c3a39676282d91cc8daaa2663610449b5e7d",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "08822e43a9e30dfb4036164d30701238da03cb0785c76566a15dcbcf8eda5f8a", ".modelhub_state/market_intelligence.json": "511a260cfd0736232fcd8fb5f501281ff0e8eaf6029027d039b7d1969666129f",
".modelhub_state/official_capabilities.json": "45e3e5ccc8d8e3bfd0089f8843c39feb149895b2de3520f9d47d8af8b2a81188", ".modelhub_state/official_capabilities.json": "ae813673d622ddc2ef11a7a5225ca7dccc04d5283fbddd7dcc1fd81b8ca4683d",
".modelhub_state/outcome_checkpoint.json": "704adf4a0379763468a8a7ae588bdd62247269b6d02a1df9371abfc3faf5b849", ".modelhub_state/outcome_checkpoint.json": "4eeeb9925469c4623c163e159bca71517afeec23558ff30723dbec5c0735dbe4",
".modelhub_state/queue_cleanup_latest.json": "fd2be7e92d633f07fd16f4af361876507c190447dc205b270d3e0d74aca9321e", ".modelhub_state/queue_cleanup_latest.json": "fd2be7e92d633f07fd16f4af361876507c190447dc205b270d3e0d74aca9321e",
".modelhub_state/recent_outcomes.jsonl": "29de8caa53d34c5cd69118aa9b7b19270cfeb5f2ed4f79592568a96e8c2790ab", ".modelhub_state/recent_outcomes.jsonl": "29de8caa53d34c5cd69118aa9b7b19270cfeb5f2ed4f79592568a96e8c2790ab",
".modelhub_state/recovery_active_tasks.jsonl": "60896a52cb4afee26aca58638bdb37a27530b23a2c1238fea2f0a239c590ef1a", ".modelhub_state/recovery_active_tasks.jsonl": "755e4f040b8de81cea2bdb25ac63dc2a0600bd12525b33b2d473bb439d62b6f7",
".modelhub_state/recovery_intents.jsonl": "2621a5049d4dad2b2b42d39de02ee1f76a7d82beabddd4e4d1a0746c4dab41de", ".modelhub_state/recovery_intents.jsonl": "0a4095c9b976acaca7b5238f854333392b5572a04f21c6297460a4e565baab09",
".modelhub_state/routing_intelligence.json": "783dcdd18e65a6df1db492a367c1d1f213fdc7208da4dc91eec95f41c84a2df2", ".modelhub_state/routing_intelligence.json": "783dcdd18e65a6df1db492a367c1d1f213fdc7208da4dc91eec95f41c84a2df2",
".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799", ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
".modelhub_state/worker_crashes.jsonl": "8f862697b8c8286a6ac8130827f91487a3eb07ecaf4af7ee3de2915d925deb10", ".modelhub_state/worker_crashes.jsonl": "8f862697b8c8286a6ac8130827f91487a3eb07ecaf4af7ee3de2915d925deb10",
"ledger/submissions.jsonl": "73fd1fbb571d3b91c604375fd6524bfc6cc65f8374093f8f1c616d8c0ddd8eb1", "ledger/submissions.jsonl": "73fd1fbb571d3b91c604375fd6524bfc6cc65f8374093f8f1c616d8c0ddd8eb1",
"outcomes/submissions.jsonl": "00f1293a1745a791cf5925e36a65e976a881aaff43aa93b9c9a97f470b91ed05" "outcomes/submissions.jsonl": "42e2e5ae3280f511c5f0d372c7001ef619fc9f86e209c6dd8cb3b04fb289fb6a"
}, },
"generation": 17549, "generation": 17550,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-27T21:36:15.961758+00:00", "updatedAt": "2026-09-27T21:38:26.287876+00:00",
"writerId": "6e8ddfbd92ca45ccaf79298516f8a6ea" "writerId": "6e8ddfbd92ca45ccaf79298516f8a6ea"
} }

2
outcomes/submissions.jsonl
View File

@@ -437,9 +437,7 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998195+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "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": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:13.509125+00:00", "targetGpu": "Biren_166m", "taskId": "4991811", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998195+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "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": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:13.509125+00:00", "targetGpu": "Biren_166m", "taskId": "4991811", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:33:30.477748+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:08.713395+00:00", "targetGpu": "Biren_166m", "taskId": "4991852", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:33:30.477748+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:08.713395+00:00", "targetGpu": "Biren_166m", "taskId": "4991852", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477723+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634956, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:20.876763+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991856", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477723+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634956, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:20.876763+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991856", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477648+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:37.185982+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991860", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477642+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "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": 9093261938, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "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": 9093261938}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:37.284265+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991861", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477642+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "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": 9093261938, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "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": 9093261938}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:37.284265+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991861", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477782+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612468, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "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": 17788612468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:49.284039+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991866", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T12:58:50.741624+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T04:44:11.759434+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4994057", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T12:58:50.741624+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T04:44:11.759434+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4994057", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T14:32:55.759836+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:25:35.855289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995260", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T14:32:55.759836+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:25:35.855289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995260", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T15:02:24.876266+00:00", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449487, "modelscopeLicense": "llama2", "modelscopeParams": 3204165888, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3425449487}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:49:13.744923+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4995536", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T15:02:24.876266+00:00", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449487, "modelscopeLicense": "llama2", "modelscopeParams": 3204165888, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3425449487}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:49:13.744923+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4995536", "taskType": "text-generation", "verifyResult": null}