diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 668bf05aea..c0d13be13c 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3313,7 +3313,7 @@ {"batchId": "6b444d74793e46ef963db8c5cfd2cea5", "completedAt": "2026-10-09T10:52:18.701641+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-09T10:52:15.831481+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3d9b8b829e5c4ab8b31c87c7a52097d2", "lastModified": "2026-09-16T17:27:29+00:00", "modelAddress": "https://modelscope.cn/models/ManniX-ITA/Qwen3.6-27B-A3B-Coder", "reason": null, "reconciledAt": "2026-10-09T12:57:44.775460+00:00", "repoId": "ManniX-ITA/Qwen3.6-27B-A3B-Coder", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5399159", "taskType": "text-generation"} {"batchId": "6b444d74793e46ef963db8c5cfd2cea5", "completedAt": "2026-10-09T10:52:18.701657+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-09T10:52:15.831583+00:00", "framework": "vllm_fix_tokenizer", "intentId": "027a30e1701d450a9f0bf4f9a9c88b84", "lastModified": "2026-09-16T14:52:58+00:00", "modelAddress": "https://modelscope.cn/models/ManniX-ITA/Qwen3.6-27B-A3B-CoderX", "reason": null, "reconciledAt": "2026-10-09T12:57:44.777840+00:00", "repoId": "ManniX-ITA/Qwen3.6-27B-A3B-CoderX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5399158", "taskType": "text-generation"} {"batchId": "edda2b191d404dd685b596b707fb8a00", "completedAt": "2026-10-09T12:52:32.407675+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-09T12:52:26.584453+00:00", "framework": "vllm_tokenizer_patch", "intentId": "26e41a07b1244c37be53e51edf23355c", "lastModified": "2026-10-09T12:52:13+00:00", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Diplodocus-preview-7B-JANGH7", "reason": null, "reconciledAt": "2026-10-09T12:57:44.778032+00:00", "repoId": "OsaurusAI/Diplodocus-preview-7B-JANGH7", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5401020", "taskType": "text-generation"} -{"batchId": "e807818d3d774fe7bb282076662bc778", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-09T13:09:28.989855+00:00", "framework": "vllm-mlu", "intentId": "7f5daffc6c7e4bddbacb55bdb28c664e", "lastModified": "2026-10-09T12:52:13+00:00", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Diplodocus-preview-7B-JANGH7", "repoId": "OsaurusAI/Diplodocus-preview-7B-JANGH7", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "e807818d3d774fe7bb282076662bc778", "completedAt": "2026-10-09T13:09:30.953860+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-09T13:09:28.989855+00:00", "framework": "vllm-mlu", "intentId": "7f5daffc6c7e4bddbacb55bdb28c664e", "lastModified": "2026-10-09T12:52:13+00:00", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Diplodocus-preview-7B-JANGH7", "reason": null, "repoId": "OsaurusAI/Diplodocus-preview-7B-JANGH7", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5401458", "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"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 0f327aaa90..2580a20ab3 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 3452 + "unified_success_first": 3453 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 30, @@ -13,7 +13,7 @@ "text-generation|Biren_166m|vllm_fix_tokenizer": 238, "text-generation|Cambricon_mlu-370-x4|vllm": 73, "text-generation|Cambricon_mlu-370-x4|vllm-customized": 15, - "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 168, + "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 169, "text-generation|Cambricon_mlu-370-x8|vllm": 58, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 71, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 176, @@ -39,8 +39,8 @@ "text-generation|hygon_k100-ai|vllm": 32, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 219 }, - "acceptedSinceRefresh": 3452, - "acceptedTotal": 3452, - "generatedAt": "2026-10-09T12:52:32.358173+00:00", + "acceptedSinceRefresh": 3453, + "acceptedTotal": 3453, + "generatedAt": "2026-10-09T13:09:30.861870+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index ca91c1210c..b53bace44c 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1018,3 +1018,4 @@ {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "submitTime": "2026-10-08T11:06:58.768281+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5378776", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g64-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g64-v2_B", "submitTime": "2026-10-08T11:06:58.769835+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5378775", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "submitTime": "2026-10-08T11:06:58.772405+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5378777", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"} +{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Diplodocus-preview-7B-JANGH7", "modelId": "OsaurusAI/Diplodocus-preview-7B-JANGH7", "submitTime": "2026-10-09T13:09:30.759470+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5401458", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"} diff --git a/manifest.json b/manifest.json index b82e3daddb..29c9ae46da 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "bbbd152f28624d4f0874ec83f240ba0bb648b2486ad6df0d33e332c278a5bfb1", ".modelhub_state/recent_outcomes.jsonl": "bc0a97850507899bdaaf51fd9eec98b529d686e76aafe8c86a2497986052eb08", ".modelhub_state/recovery_active_tasks.jsonl": "3237001e479bc92f9b1a9ae96b7e68af9c2313226a9d089f464d3d1a3f4ca997", - ".modelhub_state/recovery_intents.jsonl": "e2e83a1d3480826e767c3ba148505f7b9a3b07845ebfbac938656157a9e1fa1a", - ".modelhub_state/routing_intelligence.json": "57f587a5dbb9992cbdce7ae6a99cd6e8b82133c7bcdab7ac538bfc950927d9ce", + ".modelhub_state/recovery_intents.jsonl": "7bdb5516535a4108e4cf8e71b4aa3a86bba82229fed55bdae04835129fb624d2", + ".modelhub_state/routing_intelligence.json": "6344aba9aa9ba60f072012d914ad4c93846c4d434efb48cbe0de3a09c8e13c63", ".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b", ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f", - "ledger/submissions.jsonl": "3f0052004d9a61f887f8c9e51c87850e4e46e55e6d676a06ba4718d2a714cd6c", - "outcomes/submissions.jsonl": "6ee511810b3eac0c8b14633505e61af8c501b5c71a509deb5d1f37b1aa8599fd" + "ledger/submissions.jsonl": "61b6562427dd390ebcffe1c5a892f4be02efb5ee9e24528791262797c78b8708", + "outcomes/submissions.jsonl": "d57d83c74fee879c1877262afc7b40a6e7e6aae6a7b513e92c3c88568795b939" }, - "generation": 22601, - "phase": "intent", + "generation": 22602, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-10-09T13:09:29.114083+00:00", + "updatedAt": "2026-10-09T13:09:31.050270+00:00", "writerId": "dc0ce4714e0442da8f6b0a08a8a7cb03" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index b634db556d..e8227edcf0 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -915,3 +915,4 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ManniX-ITA/Qwen3.6-27B-A3B-Coder", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-08T11:54:51.560590+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "recursiveRepositoryBytes": 53342531046, "repositoryOnDiskBytes": 53342531046}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-09T10:52:17.272474+00:00", "targetGpu": "Biren_166m", "taskId": "5399159", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "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": "pending", "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": null, "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": "pending", "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": null, "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": "pending", "submitTime": "2026-10-09T13:09:30.759470+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5401458", "taskType": "text-generation", "verifyResult": null}