diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 1e69d1f78..280517551 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2493,8 +2493,8 @@ {"batchId": "c01540661eab4500bded09eff20bf072", "completedAt": "2026-09-24T12:00:46.286435+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-24T12:00:43.311731+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b6eb281a7c3348e6ba46162dadfd39c2", "lastModified": "2026-08-20T02:57:43+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX", "reason": null, "reconciledAt": "2026-09-24T13:37:19.366787+00:00", "repoId": "ornith-ai/Ornith-1.5-9B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5061115", "taskType": "text-generation"} {"batchId": "383631b53371418ea26a0f7e759b1420", "completedAt": "2026-09-24T13:26:56.309693+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-24T13:26:36.308378+00:00", "framework": "vllm-mlu", "intentId": "56a5819aa4624b05a40faf8f85adb3ff", "lastModified": "2026-09-24T13:17:11+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.6-27B-MTPLX-Optimized", "reason": null, "reconciledAt": "2026-09-24T13:37:19.367311+00:00", "repoId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5062101", "taskType": "text-generation"} {"batchId": "369a19fc688e4fa3ab98029ce2db00b7", "completedAt": "2026-09-24T13:27:05.306918+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-24T13:27:04.011776+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bcd2c27e5b264b2884b55bf747f44785", "lastModified": "2026-09-24T13:17:11+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.6-27B-MTPLX-Optimized", "reason": null, "reconciledAt": "2026-09-24T13:37:19.365564+00:00", "repoId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5062103", "taskType": "text-generation"} -{"batchId": "1ec498410b2b45bf9438bcd75da0ba0a", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-24T13:42:22.108670+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f0174defc5d44417b10c085ee9fc88c2", "lastModified": "2026-09-24T13:31:00+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "repoId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "1ec498410b2b45bf9438bcd75da0ba0a", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-24T13:42:22.108782+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1f11043bda65450ca87fe66f07451e0a", "lastModified": "2026-09-24T13:31:26+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "repoId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "1ec498410b2b45bf9438bcd75da0ba0a", "completedAt": "2026-09-24T13:42:44.427494+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-24T13:42:22.108670+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f0174defc5d44417b10c085ee9fc88c2", "lastModified": "2026-09-24T13:31:00+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "reason": null, "repoId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5062305", "taskType": "text-generation"} +{"batchId": "1ec498410b2b45bf9438bcd75da0ba0a", "completedAt": "2026-09-24T13:42:44.427512+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-24T13:42:22.108782+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1f11043bda65450ca87fe66f07451e0a", "lastModified": "2026-09-24T13:31:26+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "reason": null, "repoId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5062304", "taskType": "text-generation"} {"batchId": "f9c8240154db42b398dacf34696c5086", "completedAt": "2026-09-24T11:26:48.472659+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-24T11:26:46.008294+00:00", "framework": "vllm_tokenizer_patch", "intentId": "10a1c592a9ee4f11bef9a65c25835867", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "72ad98bd76b64878af3b85496f9b4f2a", "completedAt": "2026-09-24T03:18:53.744906+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-24T03:18:52.675723+00:00", "framework": "vllm-mlu", "intentId": "bc91c43bd85e44bda5e2f46293875f01", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "uniqueness_rejected", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} {"batchId": "874ca34580de4350a285a83f59f97111", "completedAt": "2026-09-23T20:16:01.643974+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-23T20:16:00.192953+00:00", "framework": "vllm", "intentId": "1cc8ab56290543c7b61c6e72b1b2fda8", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index d0a7d6f61..d617396ab 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2632 + "unified_success_first": 2634 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -8,7 +8,7 @@ "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 181, "text-generation|Ascend_910-b4|llamacpp": 14, "text-generation|Ascend_910-b4|vllm": 32, - "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 180, + "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 182, "text-generation|Biren_166m|vllm": 81, "text-generation|Biren_166m|vllm_fix_tokenizer": 148, "text-generation|Cambricon_mlu-370-x4|vllm": 73, @@ -38,8 +38,8 @@ "text-generation|hygon_k100-ai|vllm": 27, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 152 }, - "acceptedSinceRefresh": 2632, - "acceptedTotal": 2632, - "generatedAt": "2026-09-24T13:27:05.255543+00:00", + "acceptedSinceRefresh": 2634, + "acceptedTotal": 2634, + "generatedAt": "2026-09-24T13:42:44.366699+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 072233497..dca9ca314 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1052,3 +1052,5 @@ {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "submitTime": "2026-09-21T18:14:20.635969+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005325", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "submitTime": "2026-09-21T18:14:31.787220+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005326", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-21T18:32:49.780633+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005549", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "submitTime": "2026-09-24T13:42:43.507277+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5062305", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "submitTime": "2026-09-24T13:42:43.502361+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5062304", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} diff --git a/manifest.json b/manifest.json index 81e9a0b1c..64e8dcb0b 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "e12e3dc9b5a620b18a5eb919e6b78ad98b404a8ec3048f55dfadc06b4e7a28ba", ".modelhub_state/recent_outcomes.jsonl": "dcd1b8324c516e746e323a5ab28151cf4e04ac06f17572f85985669e45a0c2fd", ".modelhub_state/recovery_active_tasks.jsonl": "16d57ab8d888362c3c5b4cca3590651126c1c4c41194a39b13a1a3addf77d9b4", - ".modelhub_state/recovery_intents.jsonl": "b50388f9f70194c67a916350cd4e8590caafc4fb7b7765b84572ecbd5fcb8aa7", - ".modelhub_state/routing_intelligence.json": "d4090084256dc1779714504a751450489f70fd0bf535915e0a359f0296eb7dc9", + ".modelhub_state/recovery_intents.jsonl": "5e7a3920fce6aab4ee49692691e0dce7f79914954092d116c4695d9a28624210", + ".modelhub_state/routing_intelligence.json": "d538da09ae903a8bdfd6427dfb2533132ae71edfb14a6da94d52acfce502879e", ".modelhub_state/submission_exclusions.jsonl": "02c89260955c401737ae26ffb5b4cc542d98dc0cc7e31967a9c71b6b9597ba74", ".modelhub_state/worker_crashes.jsonl": "091381072c6fcac41b6a5fb5ab44ba0c1464d03b7ad63c09eaa3defdb195e9d3", - "ledger/submissions.jsonl": "88579b45a779d3b15e3a622ba47226f0ce25472451da2198d770e79be937aaab", - "outcomes/submissions.jsonl": "915474d52456a6550746e229a7a092a5e68315f91b761ae9273cf85eeaa94b67" + "ledger/submissions.jsonl": "987d325d756b0e9c8b3a499d8a93551fc8a248025c5a7c5caf7195780b86c535", + "outcomes/submissions.jsonl": "7dcb7159a3b60849e1f533ac7b50fac85abca80c0879f91f5748e8b1439ccc1e" }, - "generation": 14865, - "phase": "intent", + "generation": 14866, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-24T13:42:22.288730+00:00", + "updatedAt": "2026-09-24T13:42:44.533418+00:00", "writerId": "43e8b6eb13264ac59b8ccb41b795b9e4" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 5dc209174..a7d9dd481 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -842,3 +842,5 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-9B-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907662447, "estimatedRequiredGiB": 20.038, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 17929422825, "modelscopeLicense": null, "modelscopeParams": 8953803264, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17929422825}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-24T12:00:45.396613+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5061115", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981039, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981039}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-24T13:26:56.157380+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5062101", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981039, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981039}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-24T13:27:05.147174+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5062103", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.368, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2078351571, "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": 2118713354}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-24T13:42:43.507277+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5062305", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871528, "estimatedRequiredGiB": 2.379, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2093265193, "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": 2128608536}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-24T13:42:43.502361+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5062304", "taskType": "text-generation", "verifyResult": null}