diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 419a2058ec..0eea94c777 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1519,8 +1519,8 @@ {"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606424+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372325+00:00", "framework": "vllm", "intentId": "a6699f94ea5e4040b83445e2b0616607", "lastModified": "2026-09-14T19:52:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-20T04:29:16.005727+00:00", "repoId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970731", "taskType": "text-generation"} {"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606431+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372490+00:00", "framework": "vllm", "intentId": "1d2ad3edb92249e1b74cd97a139d7069", "lastModified": "2026-09-19T12:07:43+00:00", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "reason": null, "reconciledAt": "2026-09-20T04:29:16.002944+00:00", "repoId": "Arain119/Sophia", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970733", "taskType": "text-generation"} {"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606440+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372643+00:00", "framework": "vllm_fix_tokenizer", "intentId": "125ab23dd06044239654c35446823ae6", "lastModified": "2026-09-14T19:46:18+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-20T04:29:16.003564+00:00", "repoId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "4970734", "taskType": "text-generation"} -{"batchId": "1a6ff14963004d4981d5ac52ebe9c9b2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:29:37.041260+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ec8c2d74300749499590669f7efbd9bb", "lastModified": "2026-09-16T17:07:54+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "1a6ff14963004d4981d5ac52ebe9c9b2", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:29:37.041360+00:00", "framework": "vllm-mlu", "intentId": "01e4c9d0d29e4292b204b0412094c084", "lastModified": "2026-09-16T17:28:41+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} +{"batchId": "1a6ff14963004d4981d5ac52ebe9c9b2", "completedAt": "2026-09-20T04:29:44.397039+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:29:37.041260+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ec8c2d74300749499590669f7efbd9bb", "lastModified": "2026-09-16T17:07:54+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "reason": null, "repoId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4970761", "taskType": "text-generation"} +{"batchId": "1a6ff14963004d4981d5ac52ebe9c9b2", "completedAt": "2026-09-20T04:29:44.397066+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:29:37.041360+00:00", "framework": "vllm-mlu", "intentId": "01e4c9d0d29e4292b204b0412094c084", "lastModified": "2026-09-16T17:28:41+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "reason": null, "repoId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970762", "taskType": "text-generation"} {"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606457+00:00", "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.373005+00:00", "framework": "vllm", "intentId": "5265323f99c64cc89c94370f67aac3dd", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606454+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372955+00:00", "framework": "vllm", "intentId": "7c51582991c54dafac5e215dd0b22bdc", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606452+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372893+00:00", "framework": "transformers", "intentId": "1e10f0bd563344798e43900b7ed552e5", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index c653db3bbb..4bc16c674d 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 1659 + "unified_success_first": 1661 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -16,7 +16,7 @@ "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 79, "text-generation|Cambricon_mlu-370-x8|vllm": 45, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 23, - "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 85, + "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 86, "text-generation|Iluvatar_bi-150|llamacpp": 16, "text-generation|Iluvatar_bi-150|transformers": 6, "text-generation|Iluvatar_bi-150|vllm": 6, @@ -24,7 +24,7 @@ "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 23, "text-generation|Iluvatar_mrv-100|vllm": 61, "text-generation|Kunlunxin_p-800|vllm": 3, - "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 162, + "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 163, "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 54, "text-generation|MetaX_c-500|vllm": 104, "text-generation|Mthreads_s4000|llamacpp": 17, @@ -36,8 +36,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 106 }, - "acceptedSinceRefresh": 1659, - "acceptedTotal": 1659, - "generatedAt": "2026-09-20T04:29:13.545917+00:00", + "acceptedSinceRefresh": 1661, + "acceptedTotal": 1661, + "generatedAt": "2026-09-20T04:29:44.338480+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 8d76599607..4576f73c4f 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1019,3 +1019,5 @@ {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "submitTime": "2026-09-20T04:14:41.846486+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970590", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T04:15:36.958375+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970614", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-MT", "modelId": "BAAI/RoboBrain2.5-8B-MT", "submitTime": "2026-09-20T04:15:36.954828+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970615", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "submitTime": "2026-09-20T04:29:38.366645+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970761", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "submitTime": "2026-09-20T04:29:38.381652+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970762", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index 30566210fc..ae79e930cf 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "21a630cefff5c090992ca8360dafe8435b598ca2102f1b9990df6496329a9afe", ".modelhub_state/recent_outcomes.jsonl": "8b230beac27183f4f5f556eaa061dbc77bdcc47b761f379a572673e0fba55aaa", ".modelhub_state/recovery_active_tasks.jsonl": "0638d2720558b1218db3765fdb01aa589a02894545fbacc33eae14cd72152644", - ".modelhub_state/recovery_intents.jsonl": "1e61981ad0012b5d09b16fdb779ac95391a26c6a44aba08bd8d70d7ab245ca9d", - ".modelhub_state/routing_intelligence.json": "9b5baed3fe8e015bec8ad46e0d29531efe1e5b6f5720ff64d64422997a8ef367", + ".modelhub_state/recovery_intents.jsonl": "da61a21d86d45e47014f53a6a459cfc7a93c66225999671b974cfec2646d392f", + ".modelhub_state/routing_intelligence.json": "ced6a37ad4003ba40e8601a59357dd4a9a56fc584757b410cfa44065b2783300", ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "a3015e3e32622e1614dc70a014ce699e8eb45351404fe6c1a91fee0f80d7e075", - "outcomes/submissions.jsonl": "8cea2e3788f85c97c6fd3e151aa4f657259c2d1faedd4fa1a6d0655567bb7fd0" + "ledger/submissions.jsonl": "75eb6193faf8583ca39e9224842cfec285ec09fde90f1b4eeef333af9843a0b2", + "outcomes/submissions.jsonl": "3a179d6a5748cdd95bc1cd70f831cb75897c001128ea9f5401c4868dbfe2454a" }, - "generation": 10197, - "phase": "intent", + "generation": 10198, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-20T04:29:37.218438+00:00", + "updatedAt": "2026-09-20T04:29:44.515366+00:00", "writerId": "f67e4ec113c04968a9d9484fb8e36bd4" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index af55745814..5d6e0d9fab 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1044,3 +1044,5 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:26:51.246271+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970731", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:26:58.076866+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970733", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:27:06.277205+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970734", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:29:38.366645+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970761", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:29:38.381652+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970762", "taskType": "text-generation", "verifyResult": null}