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

state: generation 22761 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-09 22:20:59 +00:00
parent 05cac76a58
commit 8805e101ad
8 changed files with 1993 additions and 2160 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2843,7 +2843,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-09T22:05:57.353696+00:00", "generatedAt": "2026-10-09T22:18:54.284678+00:00",
"summary": { "summary": {
"activeBlockCount": 142, "activeBlockCount": 142,
"byGpuFramework": { "byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -443,7 +443,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-09T22:17:35.173500+00:00", "generatedAt": "2026-10-09T22:20:35.676649+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,

765
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

122
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-09T22:05:57.269289+00:00", "generatedAt": "2026-10-09T22:18:54.196242+00:00",
"lastSyncTime": "2026-10-09T22:05:56.970146+00:00", "lastSyncTime": "2026-10-09T22:18:53.970693+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -4517,10 +4517,10 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 180, "ambiguous_runtime": 181,
"参数/模板问题": 4 "参数/模板问题": 4
}, },
"failureCount": 184, "failureCount": 185,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -4530,8 +4530,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 184, "total": 185,
"unresolvedFailureCount": 184 "unresolvedFailureCount": 185
}, },
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 61, "attributableFailureCount": 61,
@@ -5046,9 +5046,9 @@
}, },
"Sunrise_pt-200-x1|vllm|text-generation": { "Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 623, "attributableFailureCount": 623,
"decisionFailureRate": 0.9889, "decisionFailureRate": 0.9873,
"decisionSuccessRate": 0.0111, "decisionSuccessRate": 0.0127,
"decisionTotal": 630, "decisionTotal": 631,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 109, "ambiguous_runtime": 109,
"architecture_compatibility": 43, "architecture_compatibility": 43,
@@ -5063,16 +5063,16 @@
"参数/模板问题": 9 "参数/模板问题": 9
}, },
"failureCount": 958, "failureCount": 958,
"failureRate": 0.9927, "failureRate": 0.9917,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 217, "platformFailureCount": 217,
"successCount": 7, "successCount": 8,
"successRate": 0.0073, "successRate": 0.0083,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 965, "total": 966,
"unresolvedFailureCount": 118 "unresolvedFailureCount": 118
}, },
"Sunrise_pt-200-x1|vllm|unknown": { "Sunrise_pt-200-x1|vllm|unknown": {
@@ -5576,9 +5576,9 @@
}, },
"vllm": { "vllm": {
"attributableFailureCount": 3690, "attributableFailureCount": 3690,
"decisionFailureRate": 0.9718, "decisionFailureRate": 0.9716,
"decisionSuccessRate": 0.0282, "decisionSuccessRate": 0.0284,
"decisionTotal": 3797, "decisionTotal": 3798,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1605, "ambiguous_runtime": 1605,
"architecture_compatibility": 112, "architecture_compatibility": 112,
@@ -5595,13 +5595,13 @@
"参数/模板问题": 83 "参数/模板问题": 83
}, },
"failureCount": 6259, "failureCount": 6259,
"failureRate": 0.9832, "failureRate": 0.983,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 881, "platformFailureCount": 881,
"successCount": 107, "successCount": 108,
"successRate": 0.0168, "successRate": 0.017,
"total": 6366, "total": 6367,
"unresolvedFailureCount": 1688 "unresolvedFailureCount": 1688
}, },
"vllm-customized": { "vllm-customized": {
@@ -5704,7 +5704,7 @@
"decisionSuccessRate": 0.0269, "decisionSuccessRate": 0.0269,
"decisionTotal": 186, "decisionTotal": 186,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 406, "ambiguous_runtime": 407,
"backend_operator": 10, "backend_operator": 10,
"framework_architecture_unsupported": 52, "framework_architecture_unsupported": 52,
"memory_capacity": 10, "memory_capacity": 10,
@@ -5713,15 +5713,15 @@
"tokenizer_compatibility": 96, "tokenizer_compatibility": 96,
"参数/模板问题": 16 "参数/模板问题": 16
}, },
"failureCount": 630, "failureCount": 631,
"failureRate": 0.9921, "failureRate": 0.9921,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 27, "platformFailureCount": 27,
"successCount": 5, "successCount": 5,
"successRate": 0.0079, "successRate": 0.0079,
"total": 635, "total": 636,
"unresolvedFailureCount": 422 "unresolvedFailureCount": 423
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"attributableFailureCount": 166, "attributableFailureCount": 166,
@@ -5752,7 +5752,7 @@
"unresolvedFailureCount": 307 "unresolvedFailureCount": 307
} }
}, },
"generatedAt": "2026-10-09T22:05:57.254376+00:00", "generatedAt": "2026-10-09T22:18:54.183127+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 129, "attributableFailureCount": 129,
@@ -5984,7 +5984,7 @@
"decisionSuccessRate": 0.066, "decisionSuccessRate": 0.066,
"decisionTotal": 106, "decisionTotal": 106,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 269, "ambiguous_runtime": 270,
"backend_operator": 23, "backend_operator": 23,
"framework_architecture_unsupported": 37, "framework_architecture_unsupported": 37,
"memory_capacity": 3, "memory_capacity": 3,
@@ -5997,15 +5997,15 @@
"日志缺失": 1, "日志缺失": 1,
"验证失败": 23 "验证失败": 23
}, },
"failureCount": 441, "failureCount": 442,
"failureRate": 0.9844, "failureRate": 0.9844,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 7, "successCount": 7,
"successRate": 0.0156, "successRate": 0.0156,
"total": 448, "total": 449,
"unresolvedFailureCount": 341 "unresolvedFailureCount": 342
}, },
"Kunlunxin_r-200-8f": { "Kunlunxin_r-200-8f": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -6089,9 +6089,9 @@
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"attributableFailureCount": 774, "attributableFailureCount": 774,
"decisionFailureRate": 0.8856, "decisionFailureRate": 0.8846,
"decisionSuccessRate": 0.1144, "decisionSuccessRate": 0.1154,
"decisionTotal": 874, "decisionTotal": 875,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 163, "ambiguous_runtime": 163,
"architecture_compatibility": 44, "architecture_compatibility": 44,
@@ -6107,13 +6107,13 @@
"验证失败": 32 "验证失败": 32
}, },
"failureCount": 1442, "failureCount": 1442,
"failureRate": 0.9351, "failureRate": 0.9345,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 244, "platformFailureCount": 244,
"successCount": 100, "successCount": 101,
"successRate": 0.0649, "successRate": 0.0655,
"total": 1542, "total": 1543,
"unresolvedFailureCount": 424 "unresolvedFailureCount": 424
}, },
"Vastai_va16": { "Vastai_va16": {
@@ -18956,9 +18956,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 12 "ambiguous_runtime": 13
}, },
"failureCount": 12, "failureCount": 13,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelType": "mini_k3", "modelType": "mini_k3",
@@ -18970,8 +18970,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 12, "total": 13,
"unresolvedFailureCount": 12 "unresolvedFailureCount": 13
}, },
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none": { "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -23744,7 +23744,7 @@
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0, "decisionSuccessRate": 1.0,
"decisionTotal": 5, "decisionTotal": 6,
"failureBreakdown": {}, "failureBreakdown": {},
"failureCount": 0, "failureCount": 0,
"failureRate": 0.0, "failureRate": 0.0,
@@ -23754,11 +23754,11 @@
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"quantizationMethod": "none", "quantizationMethod": "none",
"successCount": 5, "successCount": 6,
"successRate": 1.0, "successRate": 1.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 5, "total": 6,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none": { "Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none": {
@@ -47111,9 +47111,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 12 "ambiguous_runtime": 13
}, },
"failureCount": 12, "failureCount": 13,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30, "loadSizeLog2Bucket": 30,
@@ -47126,8 +47126,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 12, "total": 13,
"unresolvedFailureCount": 12 "unresolvedFailureCount": 13
}, },
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none|33": { "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none|33": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -54550,7 +54550,7 @@
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0, "decisionSuccessRate": 1.0,
"decisionTotal": 4, "decisionTotal": 5,
"failureBreakdown": {}, "failureBreakdown": {},
"failureCount": 0, "failureCount": 0,
"failureRate": 0.0, "failureRate": 0.0,
@@ -54561,11 +54561,11 @@
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"quantizationMethod": "none", "quantizationMethod": "none",
"successCount": 4, "successCount": 5,
"successRate": 1.0, "successRate": 1.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 4, "total": 5,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none|31": { "Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none|31": {
@@ -57984,15 +57984,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17759, "terminalRecords": 17761,
"totalRecords": 18246, "totalRecords": 18248,
"totals": { "totals": {
"attributableFailureCount": 6308, "attributableFailureCount": 6308,
"decisionFailureRate": 0.8655, "decisionFailureRate": 0.8654,
"decisionSuccessRate": 0.1345, "decisionSuccessRate": 0.1346,
"decisionTotal": 7288, "decisionTotal": 7289,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4615, "ambiguous_runtime": 4616,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 131, "backend_operator": 131,
@@ -58008,15 +58008,15 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16779, "failureCount": 16780,
"failureRate": 0.9448, "failureRate": 0.9448,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 956, "platformFailureCount": 956,
"successCount": 980, "successCount": 981,
"successRate": 0.0552, "successRate": 0.0552,
"total": 17759, "total": 17761,
"unresolvedFailureCount": 9515 "unresolvedFailureCount": 9516
}, },
"warnings": [ "warnings": [
"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。",
@@ -58078,6 +58078,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 18246, "summarizedRecords": 18248,
"version": 1 "version": 1
} }

1458
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1784
.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": "6607f91040633038b0a9f6dac20bf3d020eb66f6e5b499678505c0e3bb26c516", ".modelhub_state/architecture_compatibility_blacklist.json": "bd853942363baa1c470afbb63d84acefffa6dab73bf3995d8a7bbc6c49e64d5c",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "d40a5445311c6f7a11179d0b26dfb42969e0bb75b5771b147071491917a3b502", ".modelhub_state/market_intelligence.json": "7331647d13af470424efcd3a4a0dd843a58cb8ee821f2b9cd2a42c5115c9ab11",
".modelhub_state/official_capabilities.json": "261ede49fe1e2ee6bf6a919a8f71a8632c9f9f7dab98425ace85bdd0ee614024", ".modelhub_state/official_capabilities.json": "a274d796a5c38557279846aa8d8ff52b23804954b84eaf4090cda5ee95dd5e12",
".modelhub_state/outcome_checkpoint.json": "824386132ae397a067d7f1bcb22c15bd8173dfc182bfc654d0ba5c7bfaf36887", ".modelhub_state/outcome_checkpoint.json": "43d1b77674295573378d30446368fbf584cc02ba2196aeb7eb2cdd4c0f2096a1",
".modelhub_state/queue_cleanup_latest.json": "38724ad9092e337c52ce3db11395bc4c6d1b324caad99791ad032535d2606739", ".modelhub_state/queue_cleanup_latest.json": "38724ad9092e337c52ce3db11395bc4c6d1b324caad99791ad032535d2606739",
".modelhub_state/recent_outcomes.jsonl": "c03b3c09427b1799a3ef8a23deb08c1658f8f8d957f322d99e70ff34c22d1afa", ".modelhub_state/recent_outcomes.jsonl": "c03b3c09427b1799a3ef8a23deb08c1658f8f8d957f322d99e70ff34c22d1afa",
".modelhub_state/recovery_active_tasks.jsonl": "f8431ad5d9a0a818ca0a402cf5247bf42462a150873e506945b4ad69b67daf2f", ".modelhub_state/recovery_active_tasks.jsonl": "972a3da60818313bacb1f12a3dfbf52c0e1c56f3157d108762f52056e075b2f9",
".modelhub_state/recovery_intents.jsonl": "5278f3993083af47788644901f9cce4684cb427df6100def587d833d6970a9b4", ".modelhub_state/recovery_intents.jsonl": "386f97c8d0bd80dab436b8b472037df9e6f41355edf768ee4bf7f7bafbdf011c",
".modelhub_state/routing_intelligence.json": "d3ceb6d22b403297a9c4cf85df248647fe1e875876814914e7fa9c85f1b5f541", ".modelhub_state/routing_intelligence.json": "d3ceb6d22b403297a9c4cf85df248647fe1e875876814914e7fa9c85f1b5f541",
".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b", ".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b",
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f", ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
"ledger/submissions.jsonl": "13a8b7956660c5f6b5acd752a903f3ac5d4c794641c04948024e3aab8bfadb56", "ledger/submissions.jsonl": "13a8b7956660c5f6b5acd752a903f3ac5d4c794641c04948024e3aab8bfadb56",
"outcomes/submissions.jsonl": "110e1e1ea6c9425ce55dd03b4c75307288750b71027b3ac99b8d91921ecd37fb" "outcomes/submissions.jsonl": "3e7e1c37f562681b33c3a95a70c97f27124b10d6df92ea09c5bcb763fa7963d1"
}, },
"generation": 22760, "generation": 22761,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-09T22:17:52.966896+00:00", "updatedAt": "2026-10-09T22:20:59.814987+00:00",
"writerId": "43462b8a22de474db5c83d43b475a356" "writerId": "43462b8a22de474db5c83d43b475a356"
} }

2
outcomes/submissions.jsonl
View File

@@ -41,7 +41,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T21:51:48.716995+00:00", "modelId": "Abiray/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e2a7b7c51552e96dae7e97291f0664b9c7fbde7d5b1322eb96e684dc410a4ec3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712768, "estimatedRequiredGiB": 12.192, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10909231864, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10909231864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T13:51:12.945092+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4720102", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T21:51:48.716995+00:00", "modelId": "Abiray/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e2a7b7c51552e96dae7e97291f0664b9c7fbde7d5b1322eb96e684dc410a4ec3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712768, "estimatedRequiredGiB": 12.192, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10909231864, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10909231864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T13:51:12.945092+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4720102", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T22:32:41.015110+00:00", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "abb02b8a1726c2017f3e58267b0dcef5c53ad69497de685319b66fb05de32644", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1908528192, "estimatedRequiredGiB": 5.052, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4520619479, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1791080448, "modelscopeTags": ["license:apache-2.0", "library:pytorch", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4520619479}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.086935+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4720553", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T22:32:41.015110+00:00", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "abb02b8a1726c2017f3e58267b0dcef5c53ad69497de685319b66fb05de32644", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1908528192, "estimatedRequiredGiB": 5.052, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4520619479, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1791080448, "modelscopeTags": ["license:apache-2.0", "library:pytorch", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4520619479}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.086935+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4720553", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T22:32:41.015128+00:00", "modelId": "Abiray/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "47b99bf102c8c855259a4427d2ee4726c9c38833b231e86c64e74198958fa242", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712768, "estimatedRequiredGiB": 12.192, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10909231864, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10909231864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.090401+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4720554", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T22:32:41.015128+00:00", "modelId": "Abiray/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "47b99bf102c8c855259a4427d2ee4726c9c38833b231e86c64e74198958fa242", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712768, "estimatedRequiredGiB": 12.192, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10909231864, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10909231864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.090401+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4720554", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499797+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.090028+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725841", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499713+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.091884+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725848", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499713+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.091884+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725848", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499785+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.019663+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725846", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499785+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.019663+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725846", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499736+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.095472+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725851", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499736+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.095472+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725851", "taskType": "text-generation", "verifyResult": null}
@@ -197,7 +196,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T02:22:55.559751+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1232059012, "estimatedRequiredGiB": 1.379, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233907698, "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": "2026-09-21T15:02:24.876390+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": 1233907698}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T18:22:48.751608+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5005404", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T02:22:55.559751+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1232059012, "estimatedRequiredGiB": 1.379, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233907698, "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": "2026-09-21T15:02:24.876390+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": 1233907698}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T18:22:48.751608+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5005404", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T02:22:55.559801+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3054596816, "estimatedRequiredGiB": 3.416, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 3056444703, "modelscopeLicense": null, "modelscopeParams": 1122504704, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3056444703}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T18:22:48.756508+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005406", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T02:22:55.559801+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3054596816, "estimatedRequiredGiB": 3.416, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 3056444703, "modelscopeLicense": null, "modelscopeParams": 1122504704, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3056444703}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T18:22:48.756508+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005406", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T02:26:33.565841+00:00", "modelId": "nm-testing/tinyllama-oneshot-w4a16-channel-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 747618112, "estimatedRequiredGiB": 0.838, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 749466433, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 749466433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T18:22:48.845075+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005433", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T02:26:33.565841+00:00", "modelId": "nm-testing/tinyllama-oneshot-w4a16-channel-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 747618112, "estimatedRequiredGiB": 0.838, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 749466433, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 749466433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T18:22:48.845075+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005433", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563242+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031556216, "estimatedRequiredGiB": 2.28, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039918195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:50.449911+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006044", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563225+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030769952, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039132310}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:50.451970+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006042", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563225+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030769952, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039132310}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:50.451970+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006042", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563212+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:51.057293+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006049", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563212+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:51.057293+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006049", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563180+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:50.750203+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006047", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563180+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:50.750203+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006047", "taskType": "text-generation", "verifyResult": null}