diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 634afb105e..79652f1693 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2567,7 +2567,7 @@ {"batchId": "26e04e27418845d298f1a54d748f1861", "completedAt": "2026-09-28T19:24:03.731151+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-28T19:24:01.486299+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4e22c3ad8b34495ea2050d2b80269fd3", "lastModified": "2026-09-28T19:03:37+00:00", "modelAddress": "https://modelscope.cn/models/juspay/xor-lite", "reason": null, "reconciledAt": "2026-09-29T04:51:29.701724+00:00", "repoId": "juspay/xor-lite", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5154910", "taskType": "text-generation"} {"batchId": "26e04e27418845d298f1a54d748f1861", "completedAt": "2026-09-28T19:24:03.731165+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-28T19:24:01.486410+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1f601f11292b43e586dda40ffcfb9993", "lastModified": "2026-09-28T18:59:54+00:00", "modelAddress": "https://modelscope.cn/models/juspay/xor-nvfp4", "reason": null, "reconciledAt": "2026-09-29T04:51:29.700565+00:00", "repoId": "juspay/xor-nvfp4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5154909", "taskType": "text-generation"} {"batchId": "45792a75d9a4468cb8a67b51b95b60a9", "completedAt": "2026-09-29T04:43:19.204040+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-29T04:41:28.290592+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ad4417496a9c48369b0b8743eae3c698", "lastModified": "2026-09-04T03:50:10+00:00", "modelAddress": "https://modelscope.cn/models/IFM/K2-Horizon-MoVA-36B-A4B-FP8", "reason": null, "reconciledAt": "2026-09-29T04:51:29.701522+00:00", "repoId": "IFM/K2-Horizon-MoVA-36B-A4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5163154", "taskType": "text-generation"} -{"batchId": "e76d1cade5614b2c8fe671fa1012c172", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-29T04:58:29.089942+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4d2acd152fce4344b20aeecdc2452057", "lastModified": "2026-09-03T05:57:31+00:00", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-4.2-3b", "repoId": "ibm-granite/granite-4.2-3b", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "e76d1cade5614b2c8fe671fa1012c172", "completedAt": "2026-09-29T05:00:30.517173+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-29T04:58:29.089942+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4d2acd152fce4344b20aeecdc2452057", "lastModified": "2026-09-03T05:57:31+00:00", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-4.2-3b", "reason": null, "repoId": "ibm-granite/granite-4.2-3b", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5163383", "taskType": "text-generation"} {"batchId": "179e9ecfe35348deb44f3c5be7efe247", "completedAt": "2026-09-26T04:54:18.911541+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-26T04:54:16.299502+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f015fa059f0d4b85abd1ea1620d3a8cd", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "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"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index f74ed7a6d4..d415888962 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2706 + "unified_success_first": 2707 }, "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": 16, "text-generation|Ascend_910-b4|vllm": 32, - "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 202, + "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 203, "text-generation|Biren_166m|vllm": 81, "text-generation|Biren_166m|vllm_fix_tokenizer": 149, "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": 2706, - "acceptedTotal": 2706, - "generatedAt": "2026-09-29T04:43:19.153238+00:00", + "acceptedSinceRefresh": 2707, + "acceptedTotal": 2707, + "generatedAt": "2026-09-29T05:00:30.464140+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 5ecf07c5f8..89aed12a0a 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1024,3 +1024,4 @@ {"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/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-09-26T08:01:50.847636+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5097139", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-09-26T08:18:32.495861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5097281", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-4.2-3b", "modelId": "ibm-granite/granite-4.2-3b", "submitTime": "2026-09-29T05:00:30.349080+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5163383", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} diff --git a/manifest.json b/manifest.json index 62a7365360..8ba4b62cc2 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "efbb274df22875a030d458e3d21bcc20ea98862a900d8859bf81b3f4d2d4a704", ".modelhub_state/recent_outcomes.jsonl": "1f6ea975cd2deaf85a0cb3e87122886a82ce660a2c45914eb44108c20cd172e0", ".modelhub_state/recovery_active_tasks.jsonl": "017eccfc119696b3bacedca8aefa3fc3860b68781d32f284385b1e5df6e8218e", - ".modelhub_state/recovery_intents.jsonl": "e9e4f900a8fd5b9e803d828f44870ff23b996ba779b2e249edddfa2a8a44a13b", - ".modelhub_state/routing_intelligence.json": "7b6d88b3e3b1b7d507c85e5afba1de031c61137c3b84e9b5e28aa67b32edb0f1", + ".modelhub_state/recovery_intents.jsonl": "aa5d8bb2bfe2df8eabb878a4a113c029b1dfe24b9957afc0439fef0eaef79228", + ".modelhub_state/routing_intelligence.json": "acb81a3a09d76ce53641fd9d14fdb5ff0c74acc6a7ab543aa98136b2acf1207c", ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799", ".modelhub_state/worker_crashes.jsonl": "05bcde79076023fd20785b8270312f776430b95a2d4322ee53ef24e354c39f06", - "ledger/submissions.jsonl": "0dbdbceaac426dd3e3fe176b62a9cfae9632e3fd4320757363b96455af5c5057", - "outcomes/submissions.jsonl": "f3c1dc8ec4629f997e1a19a369591b7dd1763160d6b918f6e8bce5609c5b9102" + "ledger/submissions.jsonl": "da612faf6d28e17baada4406b8921f88a42efb4b461595eba214ce33a53a4859", + "outcomes/submissions.jsonl": "8619287cacd1b78c8c756f4a2a3930e0f204c9618e66ad607f15980d8f55032f" }, - "generation": 18252, - "phase": "intent", + "generation": 18253, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-29T04:58:29.290928+00:00", + "updatedAt": "2026-09-29T05:00:30.641097+00:00", "writerId": "9d958b95ce4146c9939da0f14b9201ff" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index b19e8f2676..447fe21f48 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -817,3 +817,4 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-29T03:24:28.551006+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T19:24:03.456200+00:00", "targetGpu": "Vastai_va16", "taskId": "5154910", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-29T03:24:28.551031+00:00", "modelId": "juspay/xor-nvfp4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 41817852712, "estimatedRequiredGiB": 46.768, "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15008654192, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 41847485419}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T19:24:03.459331+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5154909", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "IFM/K2-Horizon-MoVA-36B-A4B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 48357709120, "estimatedRequiredGiB": 54.081, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 48390780116, "modelscopeLicense": "apache-2.0", "modelscopeParams": 37444792020, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:36b", "custom_tag:mova", "custom_tag:moe", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 48390780116}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-29T04:43:16.386995+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5163154", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-29T05:00:30.349080+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5163383", "taskType": "text-generation", "verifyResult": null}