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

state: generation 22756 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-10-09 22:07:56 +00:00
parent d3134e9d29
commit 7648a9597f
7 changed files with 581 additions and 450 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"
}
},
"generatedAt": "2026-10-09T21:53:37.465710+00:00",
"generatedAt": "2026-10-09T22:05:57.353696+00:00",
"summary": {
"activeBlockCount": 142,
"byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -443,7 +443,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-09T22:04:37.101073+00:00",
"generatedAt": "2026-10-09T22:07:36.374991+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

902
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

103
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-09T21:23:51.065908+00:00",
"lastSyncTime": "2026-10-09T21:23:50.776609+00:00",
"generatedAt": "2026-10-09T22:05:57.269289+00:00",
"lastSyncTime": "2026-10-09T22:05:56.970146+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -5045,10 +5045,10 @@
"unresolvedFailureCount": 8
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 622,
"attributableFailureCount": 623,
"decisionFailureRate": 0.9889,
"decisionSuccessRate": 0.0111,
"decisionTotal": 629,
"decisionTotal": 630,
"failureBreakdown": {
"ambiguous_runtime": 109,
"architecture_compatibility": 43,
@@ -5059,10 +5059,10 @@
"platform_infrastructure": 217,
"repository_structure": 75,
"runtime_memory": 1,
"tokenizer_compatibility": 180,
"tokenizer_compatibility": 181,
"参数/模板问题": 9
},
"failureCount": 957,
"failureCount": 958,
"failureRate": 0.9927,
"framework": "vllm",
"pendingCount": 0,
@@ -5072,7 +5072,7 @@
"successRate": 0.0073,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 964,
"total": 965,
"unresolvedFailureCount": 118
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -5575,10 +5575,10 @@
"unresolvedFailureCount": 6551
},
"vllm": {
"attributableFailureCount": 3689,
"attributableFailureCount": 3690,
"decisionFailureRate": 0.9718,
"decisionSuccessRate": 0.0282,
"decisionTotal": 3796,
"decisionTotal": 3797,
"failureBreakdown": {
"ambiguous_runtime": 1605,
"architecture_compatibility": 112,
@@ -5591,17 +5591,17 @@
"platform_infrastructure": 881,
"repository_structure": 470,
"runtime_memory": 66,
"tokenizer_compatibility": 420,
"tokenizer_compatibility": 421,
"参数/模板问题": 83
},
"failureCount": 6258,
"failureCount": 6259,
"failureRate": 0.9832,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 881,
"successCount": 107,
"successRate": 0.0168,
"total": 6365,
"total": 6366,
"unresolvedFailureCount": 1688
},
"vllm-customized": {
@@ -5752,7 +5752,7 @@
"unresolvedFailureCount": 307
}
},
"generatedAt": "2026-10-09T21:23:51.050975+00:00",
"generatedAt": "2026-10-09T22:05:57.254376+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 129,
@@ -6088,10 +6088,10 @@
"unresolvedFailureCount": 330
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 773,
"decisionFailureRate": 0.8855,
"decisionSuccessRate": 0.1145,
"decisionTotal": 873,
"attributableFailureCount": 774,
"decisionFailureRate": 0.8856,
"decisionSuccessRate": 0.1144,
"decisionTotal": 874,
"failureBreakdown": {
"ambiguous_runtime": 163,
"architecture_compatibility": 44,
@@ -6102,18 +6102,18 @@
"platform_infrastructure": 244,
"repository_structure": 83,
"runtime_memory": 1,
"tokenizer_compatibility": 279,
"tokenizer_compatibility": 280,
"参数/模板问题": 229,
"验证失败": 32
},
"failureCount": 1441,
"failureCount": 1442,
"failureRate": 0.9351,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 244,
"successCount": 100,
"successRate": 0.0649,
"total": 1541,
"total": 1542,
"unresolvedFailureCount": 424
},
"Vastai_va16": {
@@ -23808,6 +23808,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|zaya|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -54641,6 +54664,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|starcoder2|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|zaya|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -57937,13 +57984,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17758,
"totalRecords": 18245,
"terminalRecords": 17759,
"totalRecords": 18246,
"totals": {
"attributableFailureCount": 6307,
"attributableFailureCount": 6308,
"decisionFailureRate": 0.8655,
"decisionSuccessRate": 0.1345,
"decisionTotal": 7287,
"decisionTotal": 7288,
"failureBreakdown": {
"ambiguous_runtime": 4615,
"architecture_compatibility": 212,
@@ -57956,19 +58003,19 @@
"platform_infrastructure": 956,
"repository_structure": 742,
"runtime_memory": 101,
"tokenizer_compatibility": 690,
"tokenizer_compatibility": 691,
"参数/模板问题": 3505,
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16778,
"failureCount": 16779,
"failureRate": 0.9448,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 956,
"successCount": 980,
"successRate": 0.0552,
"total": 17758,
"total": 17759,
"unresolvedFailureCount": 9515
},
"warnings": [
@@ -58031,6 +58078,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 18245,
"summarizedRecords": 18246,
"version": 1
}

1
.modelhub_state/recovery_intents.jsonl
View File

@@ -3317,6 +3317,7 @@
{"batchId": "21f20d3019b2403c9138a840d4b1ed4a", "completedAt": "2026-10-09T14:03:53.770735+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-10-09T14:03:52.098449+00:00", "framework": "vllm", "intentId": "1d9873ed84e14c39bd9bf3302b81f11f", "lastModified": "2026-09-16T17:27:29+00:00", "modelAddress": "https://modelscope.cn/models/ManniX-ITA/Qwen3.6-27B-A3B-Coder", "reason": null, "reconciledAt": "2026-10-09T21:58:59.610703+00:00", "repoId": "ManniX-ITA/Qwen3.6-27B-A3B-Coder", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5402815", "taskType": "text-generation"}
{"batchId": "abc53a8316714ce8becfa5477f135ff7", "completedAt": "2026-10-09T19:02:14.031882+00:00", "configFingerprint": "05ede70cae27525d29b4c44e2be02476a5362f2e8a93365f5c82cd3c918aa123", "configSource": "modelhub_live", "createdAt": "2026-10-09T18:59:58.090507+00:00", "framework": "llamacpp", "intentId": "dae6cefd4b7047c78598723c046bba48", "lastModified": "2026-10-09T18:44:32+00:00", "modelAddress": "https://modelscope.cn/models/lightonai/colgrep-agent-2B-GGUF", "reason": null, "reconciledAt": "2026-10-09T21:58:59.609000+00:00", "repoId": "lightonai/colgrep-agent-2B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5407638", "taskType": "text-generation"}
{"batchId": "ac5ecfbc052e4d75ae8bb21455be4827", "completedAt": "2026-10-09T19:18:44.322464+00:00", "configFingerprint": "3b82836fb5958ba363655971ed1f15d8109ab96526648b59a9c28586a1d7b2d6", "configSource": "modelhub_live", "createdAt": "2026-10-09T19:18:43.117096+00:00", "framework": "llamacpp", "intentId": "55603b708d5147198368764ac965ec48", "lastModified": "2026-10-09T18:44:32+00:00", "modelAddress": "https://modelscope.cn/models/lightonai/colgrep-agent-2B-GGUF", "reason": null, "reconciledAt": "2026-10-09T21:58:59.608998+00:00", "repoId": "lightonai/colgrep-agent-2B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5407882", "taskType": "text-generation"}
{"batchId": "c4d7127a6ea84951995f6e5212e513a9", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-09T22:07:56.306226+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bc805f26f779445388d9b6fd5c613a65", "lastModified": "2026-10-09T18:42:19+00:00", "modelAddress": "https://modelscope.cn/models/IQuestLab/SAIL", "repoId": "IQuestLab/SAIL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "6aa7248a7b3546dba73bdb92d9a77079", "completedAt": "2026-10-07T20:18:36.848910+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T19:40:31.784067+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2f0cb6ccdecc4316b55609675cbdd668", "repoId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "6aa7248a7b3546dba73bdb92d9a77079", "completedAt": "2026-10-07T20:18:36.848903+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T19:40:31.783981+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e743bd075d9a4fef818c147bbe312063", "repoId": "ibm-granite/granite-4.2-30b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "6aa7248a7b3546dba73bdb92d9a77079", "completedAt": "2026-10-07T20:18:36.848900+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T19:40:31.783937+00:00", "framework": "vllm_fix_tokenizer", "intentId": "55a1a393950e454a964334b9ea2f0089", "repoId": "danish-foundation-models/DFM-Mimir-v1.5", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.22.1",
"checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "895b1355b55155a852ac7065a3ce2d13767ca42127febc631c5899697df46294",
".modelhub_state/architecture_compatibility_blacklist.json": "6607f91040633038b0a9f6dac20bf3d020eb66f6e5b499678505c0e3bb26c516",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "3ea9798b3dd75ef08a2e08c6624977b5aceca418ddecdea811cfea77857753a4",
".modelhub_state/official_capabilities.json": "ae421a1df338876f14a25cd2cef0ae30f8e40c4945f1662eb437121a15daaa80",
".modelhub_state/outcome_checkpoint.json": "13eb13578a84937f2c6739c24cf793a19ba8ed2933ed1bd3212df590c46e372e",
".modelhub_state/market_intelligence.json": "7402210c85febfd755226382d36bfb1246e6660144f26d15a72081e13581732e",
".modelhub_state/official_capabilities.json": "8cf8e9ab0b22666326b6e2e67c32e0c01de3d9c5c24d973e08d7a3dc9665caa0",
".modelhub_state/outcome_checkpoint.json": "824386132ae397a067d7f1bcb22c15bd8173dfc182bfc654d0ba5c7bfaf36887",
".modelhub_state/queue_cleanup_latest.json": "38724ad9092e337c52ce3db11395bc4c6d1b324caad99791ad032535d2606739",
".modelhub_state/recent_outcomes.jsonl": "c03b3c09427b1799a3ef8a23deb08c1658f8f8d957f322d99e70ff34c22d1afa",
".modelhub_state/recovery_active_tasks.jsonl": "2f8d8a80420e95b6cfadd6ea52d7ac974aad6bcf1c8bb71759847924017f2b4e",
".modelhub_state/recovery_intents.jsonl": "6495da5ecc6e1726c38104f210aba7caae53265a98fd2ef27dea3e176344aead",
".modelhub_state/recovery_intents.jsonl": "ead51e4ba952c6295e1b4fa908a793114d96fc6954641ae4ac2b4fa741d0a94a",
".modelhub_state/routing_intelligence.json": "7feeb8c03d0e6dc06419e40db3c47801ecbb1be95258832962d5af5a7567ec18",
".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b",
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
"ledger/submissions.jsonl": "c741c044312bdb2b17ad382b3c8411ad3fadebf14dc93ea6844a629465e02d77",
"outcomes/submissions.jsonl": "7062855c5a113ae9dcf56a7e855aed208e6c97737885e70c0f3450eb87e4b09f"
"outcomes/submissions.jsonl": "bfa4e24ea741c540b6af72e11a2ca473608f79de40de2927ba063fe134ca7d4b"
},
"generation": 22755,
"phase": "cycle",
"generation": 22756,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-10-09T22:04:55.900476+00:00",
"updatedAt": "2026-10-09T22:07:56.452032+00:00",
"writerId": "43462b8a22de474db5c83d43b475a356"
}

3
outcomes/submissions.jsonl
View File

@@ -158,7 +158,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T01:35:45.556145+00:00", "modelId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7003604832, "estimatedRequiredGiB": 7.829, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7005626643, "modelscopeLicense": "llama2", "modelscopeParams": 6738415616, "modelscopeTags": ["license:llama2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7005626643}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:14:08.972708+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984272", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T01:35:45.556088+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809686744}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:20:07.435588+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984361", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T01:35:45.556160+00:00", "modelId": "RedHatAI/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720441937, "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": 8720441937}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:20:14.310450+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984367", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T01:52:39.246349+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "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": 17788663591}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:49:20.875289+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984851", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T02:15:17.867333+00:00", "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658256, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:59:59.555224+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985000", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-21T02:42:24.494032+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-20T18:39:53.164098+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4985692", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T03:02:20.757732+00:00", "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658310, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658310}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:17.970020+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985910", "taskType": "text-generation", "verifyResult": null}
@@ -904,6 +903,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-09T18:56:56.464950+00:00", "modelId": "ManniX-ITA/Qwen3.6-27B-A3B-CoderX", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 52429184344, "estimatedRequiredGiB": 58.619, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe_text", "modelscopeFileSize": 52451782841, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26213016704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:expert-pruning", "custom_tag:code", "custom_tag:mtp", "custom_tag:omnimergekit"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 52451782841, "quantizationMethod": null, "recursiveRepositoryBytes": 52451782841, "repositoryOnDiskBytes": 52451782841}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T10:52:17.252232+00:00", "targetGpu": "Biren_166m", "taskId": "5399158", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-09T20:54:47.764094+00:00", "modelId": "OsaurusAI/Diplodocus-preview-7B-JANGH7", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6627366288, "estimatedRequiredGiB": 7.43, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1727664128, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:finance", "custom_tag:k2_horizon", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "recursiveRepositoryBytes": 6648353931, "repositoryOnDiskBytes": 6648353931}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T12:52:30.765636+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5401020", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-09T21:13:02.549148+00:00", "modelId": "OsaurusAI/Diplodocus-preview-7B-JANGH7", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6627366288, "estimatedRequiredGiB": 7.43, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6648353931, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1727664128, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:finance", "custom_tag:k2_horizon", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 6648353931, "quantizationMethod": null, "recursiveRepositoryBytes": 6648353931, "repositoryOnDiskBytes": 6648353931}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T13:09:30.759470+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5401458", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ManniX-ITA/Qwen3.6-27B-A3B-Coder", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53319307872, "estimatedRequiredGiB": 59.615, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 53342531046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26659587952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:code", "custom_tag:expert-pruning", "custom_tag:qwen3.6"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 53342531046, "quantizationMethod": null, "recursiveRepositoryBytes": 53342531046, "repositoryOnDiskBytes": 53342531046}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-09T14:03:53.551952+00:00", "targetGpu": "MetaX_c-500", "taskId": "5402815", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-09T22:05:56.970146+00:00", "modelId": "ManniX-ITA/Qwen3.6-27B-A3B-Coder", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53319307872, "estimatedRequiredGiB": 59.615, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 53342531046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26659587952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:code", "custom_tag:expert-pruning", "custom_tag:qwen3.6"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 53342531046, "quantizationMethod": null, "recursiveRepositoryBytes": 53342531046, "repositoryOnDiskBytes": 53342531046}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T14:03:53.551952+00:00", "targetGpu": "MetaX_c-500", "taskId": "5402815", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "lightonai/colgrep-agent-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "05ede70cae27525d29b4c44e2be02476a5362f2e8a93365f5c82cd3c918aa123", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1490355392, "estimatedRequiredGiB": 22.003, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 2516756480, "modelscopeTags": ["library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:code", "custom_tag:code-search", "custom_tag:colgrep", "custom_tag:agent", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "recursiveRepositoryBytes": 19687833658, "repositoryOnDiskBytes": 19687833658}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-09T19:02:12.450314+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5407638", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "lightonai/colgrep-agent-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "3b82836fb5958ba363655971ed1f15d8109ab96526648b59a9c28586a1d7b2d6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1490355392, "estimatedRequiredGiB": 22.003, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 19687833658, "modelscopeLicense": null, "modelscopeParams": 2516756480, "modelscopeTags": ["library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:code", "custom_tag:code-search", "custom_tag:colgrep", "custom_tag:agent", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 19687833658, "quantizationMethod": null, "recursiveRepositoryBytes": 19687833658, "repositoryOnDiskBytes": 19687833658}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-09T19:18:44.203926+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5407882", "taskType": "text-generation", "verifyResult": null}