state: generation 18310 (cycle)
This commit is contained in:
@@ -3280,7 +3280,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-29T07:50:06.342213+00:00",
|
||||
"generatedAt": "2026-09-29T07:59:04.105696+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 165,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-29T07:42:42.862742+00:00",
|
||||
"communityAttemptedAt": "2026-09-29T08:00:29.372492+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-29T07:42:42.862742+00:00",
|
||||
"communityUpdatedAt": "2026-09-29T08:00:29.372492+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-29T02:13:21.967349+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-29T07:57:39.565044+00:00",
|
||||
"generatedAt": "2026-09-29T08:00:29.372492+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-29T07:57:39.565044+00:00",
|
||||
"catalogUpdatedAt": "2026-09-29T08:00:29.372492+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-29T07:57:39.565044+00:00",
|
||||
"generatedAt": "2026-09-29T08:00:29.372492+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6311,6 +6311,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-29T07:57:39.565044+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-29T08:00:29.372492+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-29T07:50:06.246501+00:00",
|
||||
"lastSyncTime": "2026-09-29T07:50:05.961860+00:00",
|
||||
"generatedAt": "2026-09-29T07:59:04.015459+00:00",
|
||||
"lastSyncTime": "2026-09-29T07:59:03.756289+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -5429,21 +5429,21 @@
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 15,
|
||||
"platform_infrastructure": 20,
|
||||
"platform_infrastructure": 21,
|
||||
"tokenizer_compatibility": 91,
|
||||
"参数/模板问题": 6
|
||||
},
|
||||
"failureCount": 141,
|
||||
"failureCount": 142,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 20,
|
||||
"platformFailureCount": 21,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 141,
|
||||
"total": 142,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -6110,18 +6110,18 @@
|
||||
"framework_architecture_unsupported": 34,
|
||||
"memory_capacity": 10,
|
||||
"model_load": 9,
|
||||
"platform_infrastructure": 20,
|
||||
"platform_infrastructure": 21,
|
||||
"tokenizer_compatibility": 91,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 512,
|
||||
"failureCount": 513,
|
||||
"failureRate": 0.9903,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 20,
|
||||
"platformFailureCount": 21,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0097,
|
||||
"total": 517,
|
||||
"total": 518,
|
||||
"unresolvedFailureCount": 339
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
@@ -6153,7 +6153,7 @@
|
||||
"unresolvedFailureCount": 197
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-29T07:50:06.232317+00:00",
|
||||
"generatedAt": "2026-09-29T07:59:04.002711+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6499,21 +6499,21 @@
|
||||
"context_length": 39,
|
||||
"framework_architecture_unsupported": 160,
|
||||
"memory_capacity": 113,
|
||||
"platform_infrastructure": 227,
|
||||
"platform_infrastructure": 228,
|
||||
"repository_structure": 83,
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 273,
|
||||
"参数/模板问题": 228,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 1399,
|
||||
"failureCount": 1400,
|
||||
"failureRate": 0.9377,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 227,
|
||||
"platformFailureCount": 228,
|
||||
"successCount": 93,
|
||||
"successRate": 0.0623,
|
||||
"total": 1492,
|
||||
"total": 1493,
|
||||
"unresolvedFailureCount": 422
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -20986,21 +20986,21 @@
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 1
|
||||
"platform_infrastructure": 2
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "qwen3_5_mtp",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"platformFailureCount": 2,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
|
||||
@@ -49087,22 +49087,23 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 28,
|
||||
"modelType": "qwen3_5_mtp",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"platformFailureCount": 1,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5|none|32": {
|
||||
@@ -52209,8 +52210,8 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17095,
|
||||
"totalRecords": 17316,
|
||||
"terminalRecords": 17096,
|
||||
"totalRecords": 17317,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6128,
|
||||
"decisionFailureRate": 0.8636,
|
||||
@@ -52225,7 +52226,7 @@
|
||||
"framework_architecture_unsupported": 2183,
|
||||
"memory_capacity": 1206,
|
||||
"model_load": 550,
|
||||
"platform_infrastructure": 938,
|
||||
"platform_infrastructure": 939,
|
||||
"repository_structure": 742,
|
||||
"runtime_memory": 101,
|
||||
"tokenizer_compatibility": 681,
|
||||
@@ -52233,14 +52234,14 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16127,
|
||||
"failureCount": 16128,
|
||||
"failureRate": 0.9434,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 938,
|
||||
"platformFailureCount": 939,
|
||||
"successCount": 968,
|
||||
"successRate": 0.0566,
|
||||
"total": 17095,
|
||||
"total": 17096,
|
||||
"unresolvedFailureCount": 9061
|
||||
},
|
||||
"warnings": [
|
||||
@@ -52270,7 +52271,6 @@
|
||||
"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 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 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 Kunlunxin_p-800|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 MetaX_c-500|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b4|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|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -52295,10 +52295,11 @@
|
||||
"组合 hygon_k100-ai|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|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 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 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
"组合 Vastai_va16|vllm|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|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",
|
||||
"summarizedRecords": 17316,
|
||||
"summarizedRecords": 17317,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.22.1",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "cb1ee1f6c9107f822c58fbb5c8b85b2f016291a58db68888efbcf8abd6175f36",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "65ed548bff3607e2fc735ed21fe3591bf07d07c432a8c9ae83b5d607a3345375",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "7c5885ed974b87183ddae78372abe461c665c45ffa85c1cf5a49c5f62e366019",
|
||||
".modelhub_state/official_capabilities.json": "6047728621266c685362cc382d0427011ab2387e0c18e035d6545f79b938ed14",
|
||||
".modelhub_state/outcome_checkpoint.json": "9b8aef785b27993113aa89a7272b9fdb6584ea5078178bef09a514557fdf7296",
|
||||
".modelhub_state/market_intelligence.json": "7e3b136d240240fdc0897b1845ebf28f7d6564c8150d6bb3a3a509f76045068e",
|
||||
".modelhub_state/official_capabilities.json": "8882930a0a52a643c532213069f5b5d8cecc0816753f902a923e5df4d17f64e3",
|
||||
".modelhub_state/outcome_checkpoint.json": "f53623105e42dc39c26ecca6368bc3f80407bf0b3e089374742d210d2758c4a3",
|
||||
".modelhub_state/queue_cleanup_latest.json": "efbb274df22875a030d458e3d21bcc20ea98862a900d8859bf81b3f4d2d4a704",
|
||||
".modelhub_state/recent_outcomes.jsonl": "1f6ea975cd2deaf85a0cb3e87122886a82ce660a2c45914eb44108c20cd172e0",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "c4fa15d793fac7e9d4b925b031ceeb3c152f4b709096708347985307c667802f",
|
||||
".modelhub_state/recovery_intents.jsonl": "371f6bf28a0cdf27deb54cbb522995ab6bbfb51383f18f529855a6c1cfb9e5d8",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "86feafd95f7caa92405056a52f8cb92c7d27debc4784c219e96b3d3e39635c75",
|
||||
".modelhub_state/recovery_intents.jsonl": "f2515638aa114e19e7987cca2b3ba7120dc13e44819a1cd99a883c4698552371",
|
||||
".modelhub_state/routing_intelligence.json": "aea169fcd28ee89ddb8a2c374f7bebe61ebeeecce81dcae8cc03517271315c3a",
|
||||
".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
|
||||
".modelhub_state/worker_crashes.jsonl": "05bcde79076023fd20785b8270312f776430b95a2d4322ee53ef24e354c39f06",
|
||||
"ledger/submissions.jsonl": "20c1a66cb672b102b1ad0945fbea70fae2cd974042a1ce376ad7aa281016c4e9",
|
||||
"outcomes/submissions.jsonl": "60dcdc50defe429d76db49fe739ea93f210db3a2deefe834b43f56d148889077"
|
||||
"outcomes/submissions.jsonl": "1ff73e79ed0dae11b6f215c5595ddd549d273efe6c948fdc7e8835c57c54fe47"
|
||||
},
|
||||
"generation": 18309,
|
||||
"generation": 18310,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-29T07:58:00.088379+00:00",
|
||||
"updatedAt": "2026-09-29T08:01:33.652085+00:00",
|
||||
"writerId": "9d958b95ce4146c9939da0f14b9201ff"
|
||||
}
|
||||
|
||||
@@ -13,7 +13,6 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T22:44:15.950234+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "05c5a771e8ede0f61c61c1696314e8cb295d87d07704eedc68e43f7483931e45", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:39:36.525018+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4650654", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503426+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084014480, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093198689, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093198689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.389266+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657903", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503472+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19509024201, "estimatedRequiredGiB": 21.828, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19530936726, "modelscopeLicense": null, "modelscopeParams": 5419330688, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19530936726}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.419799+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657897", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503479+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-8bit", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 451270785, "estimatedRequiredGiB": 0.534, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 478002291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 119465472, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 478002291}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.487200+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657899", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503418+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293335560, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295942065, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295942065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.393987+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657908", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503463+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020563851, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "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": 12020563851}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.392742+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657912", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503359+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 36828222561, "estimatedRequiredGiB": 41.183, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 36850135087, "modelscopeLicense": null, "modelscopeParams": 9749130368, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36850135087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.349157+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657906", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user