diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 5cf4e1d8b3..b28af95d24 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2564,8 +2564,8 @@ {"batchId": "6a2a87a76b754ef9bfe7e5c8ecae1652", "completedAt": "2026-09-28T19:07:06.685882+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-28T19:05:42.266319+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c5a8e29b36454b1f911247e71feb71a5", "lastModified": "2026-09-28T18:59:54+00:00", "modelAddress": "https://modelscope.cn/models/juspay/xor-nvfp4", "reason": null, "reconciledAt": "2026-09-28T19:16:19.772443+00:00", "repoId": "juspay/xor-nvfp4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5154636", "taskType": "text-generation"} {"batchId": "1a5736eabe8746a9b337605d5d70e2be", "completedAt": "2026-09-28T19:08:37.676608+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-28T19:07:19.192813+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f5bdaf0f9581427d8fc385bebde3c18d", "lastModified": "2026-09-28T18:40:17+00:00", "modelAddress": "https://modelscope.cn/models/BananaMind/TernaryBananaMind-10M", "reason": null, "reconciledAt": "2026-09-28T19:16:19.770246+00:00", "repoId": "BananaMind/TernaryBananaMind-10M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5154643", "taskType": "text-generation"} {"batchId": "1a5736eabe8746a9b337605d5d70e2be", "completedAt": "2026-09-28T19:08:37.676625+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-28T19:07:19.192932+00:00", "framework": "vllm_fix_tokenizer", "intentId": "742e95fcaa51496195da2626687856f0", "lastModified": "2026-09-28T18:39:34+00:00", "modelAddress": "https://modelscope.cn/models/peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "reason": null, "reconciledAt": "2026-09-28T19:16:19.771237+00:00", "repoId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5154642", "taskType": "text-generation"} -{"batchId": "26e04e27418845d298f1a54d748f1861", "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", "repoId": "juspay/xor-lite", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} -{"batchId": "26e04e27418845d298f1a54d748f1861", "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", "repoId": "juspay/xor-nvfp4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} +{"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, "repoId": "juspay/xor-lite", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "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, "repoId": "juspay/xor-nvfp4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5154909", "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 18372ea81e..d21bc45026 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2703 + "unified_success_first": 2705 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -32,14 +32,14 @@ "text-generation|Mthreads_s4000|llamacpp": 21, "text-generation|Mthreads_s4000|vllm": 120, "text-generation|Sunrise_pt-200-x1|vllm": 87, - "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 110, - "text-generation|Vastai_va16|vllm_fix_tokenizer": 101, + "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 111, + "text-generation|Vastai_va16|vllm_fix_tokenizer": 102, "text-generation|hygon_k100-ai|llamacpp": 22, "text-generation|hygon_k100-ai|vllm": 27, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 152 }, - "acceptedSinceRefresh": 2703, - "acceptedTotal": 2703, - "generatedAt": "2026-09-28T19:08:37.578321+00:00", + "acceptedSinceRefresh": 2705, + "acceptedTotal": 2705, + "generatedAt": "2026-09-28T19:24:03.680427+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 2e804221ff..c5f742df66 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1039,3 +1039,5 @@ {"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_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/juspay/xor-lite", "modelId": "juspay/xor-lite", "submitTime": "2026-09-28T19:24:03.456200+00:00", "targetGpu": "Vastai_va16", "taskId": "5154910", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/juspay/xor-nvfp4", "modelId": "juspay/xor-nvfp4", "submitTime": "2026-09-28T19:24:03.459331+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5154909", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"} diff --git a/manifest.json b/manifest.json index d1e17443ea..c0e1eccd76 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "d09d9940cc3b3be17208fe9c9249cf654886f748a0e8ae3d2c99fbf473612f1f", ".modelhub_state/recent_outcomes.jsonl": "1dbde9c4996b0dbc395b2b06ede89ee01d228323012054151eb598a3995b826e", ".modelhub_state/recovery_active_tasks.jsonl": "eae66c487aa4502d344b8ae33d9dd0c7192728ea60b30b1c09de5f240e1b755b", - ".modelhub_state/recovery_intents.jsonl": "c4a714a96c5ef699c1714ec79b56baaf31ae34945b1004d76b8effc2a63614fd", - ".modelhub_state/routing_intelligence.json": "aad6b3549dfec65884916fc049b2ead8e56c5bdd4bd25b7e23b8773356a5b9c6", + ".modelhub_state/recovery_intents.jsonl": "2005dcff28566104d69937ac8976d5b99c9528587ebc0ecc56b88061e062dc94", + ".modelhub_state/routing_intelligence.json": "2a22275a277723b1368e1f6dc16a13a645a993ad5ca7aacde4338523757c3c6e", ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799", ".modelhub_state/worker_crashes.jsonl": "05bcde79076023fd20785b8270312f776430b95a2d4322ee53ef24e354c39f06", - "ledger/submissions.jsonl": "20b9a89f12412da13216a4795512185a1b8f445963f30e82c1a951e2b3533606", - "outcomes/submissions.jsonl": "5fbc75559acfd6b69dee22765cbe9f28fda2b1ad1ca50ca1e6e2171da878ea26" + "ledger/submissions.jsonl": "f3b675ecdfab601db686ff4d202e7d93db50725a7541cb3efd9f2a0a20359f9f", + "outcomes/submissions.jsonl": "f01f7ccdf557fb440fb4849a769217d15c6f3d0ba5d1cb50e46a07538dee5eb5" }, - "generation": 18030, - "phase": "intent", + "generation": 18031, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-28T19:24:01.701997+00:00", + "updatedAt": "2026-09-28T19:24:03.848110+00:00", "writerId": "9d958b95ce4146c9939da0f14b9201ff" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 7d26aead76..723bee2b3f 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -825,3 +825,5 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "juspay/xor-nvfp4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 41817852712, "estimatedRequiredGiB": 46.768, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "pending", "submitTime": "2026-09-28T19:07:04.848603+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5154636", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-28T19:08:37.345036+00:00", "targetGpu": "Vastai_va16", "taskId": "5154643", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "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:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-28T19:08:37.352167+00:00", "targetGpu": "Vastai_va16", "taskId": "5154642", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "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": "pending", "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": null, "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": "pending", "submitTime": "2026-09-28T19:24:03.459331+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5154909", "taskType": "text-generation", "verifyResult": null}