diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index a19c5a6492..9243e01b79 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2536,7 +2536,7 @@ {"batchId": "aeb3756006544812b0cb9f14f2592bf6", "completedAt": "2026-09-26T08:18:32.600479+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-26T08:17:51.968623+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2dd66619f68f47dc89a4b43c84402164", "lastModified": "2026-09-16T17:31:09+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-26T12:43:41.771448+00:00", "repoId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5097281", "taskType": "text-generation"} {"batchId": "2e59336363a040678d0fa496f5fdfa99", "completedAt": "2026-09-26T11:27:31.403402+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-26T11:26:52.236314+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f70ae4d47f4b46c390126502ca59f0c9", "lastModified": "2026-09-05T13:59:29+00:00", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-4.2-8b", "reason": null, "reconciledAt": "2026-09-26T12:43:41.769259+00:00", "repoId": "ibm-granite/granite-4.2-8b", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5099581", "taskType": "text-generation"} {"batchId": "5d32fc2fcbef4d6da617f25f9532887e", "completedAt": "2026-09-26T11:43:40.340062+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-26T11:43:39.306631+00:00", "framework": "vllm_fix_tokenizer", "intentId": "23c8ecb85972412a8a6f6f4da4c23a0e", "lastModified": "2026-09-05T13:59:29+00:00", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-4.2-8b", "reason": null, "reconciledAt": "2026-09-26T12:43:41.770295+00:00", "repoId": "ibm-granite/granite-4.2-8b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5099879", "taskType": "text-generation"} -{"batchId": "27112e1fd740423d8fc50ce3ac230af0", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-26T12:46:23.376740+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ccfaf6e5b9324f468b56bc11e7371599", "lastModified": "2026-09-26T12:45:14+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-5bit-MLX", "repoId": "ukisai/Swift-1.5-5bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "27112e1fd740423d8fc50ce3ac230af0", "completedAt": "2026-09-26T12:47:10.547785+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-26T12:46:23.376740+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ccfaf6e5b9324f468b56bc11e7371599", "lastModified": "2026-09-26T12:45:14+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-5bit-MLX", "reason": null, "repoId": "ukisai/Swift-1.5-5bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5100778", "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 3bbe0da939..36524f4c7b 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2675 + "unified_success_first": 2676 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -26,7 +26,7 @@ "text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 14, "text-generation|Iluvatar_mrv-100|vllm": 81, "text-generation|Kunlunxin_p-800|vllm": 64, - "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 228, + "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 229, "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 98, "text-generation|MetaX_c-500|vllm": 124, "text-generation|Mthreads_s4000|llamacpp": 20, @@ -38,8 +38,8 @@ "text-generation|hygon_k100-ai|vllm": 27, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 152 }, - "acceptedSinceRefresh": 2675, - "acceptedTotal": 2675, - "generatedAt": "2026-09-26T11:43:40.297884+00:00", + "acceptedSinceRefresh": 2676, + "acceptedTotal": 2676, + "generatedAt": "2026-09-26T12:47:10.502793+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 39859e78f8..164203a044 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1050,3 +1050,4 @@ {"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_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-5bit-MLX", "modelId": "ukisai/Swift-1.5-5bit-MLX", "submitTime": "2026-09-26T12:47:09.108765+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5100778", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} diff --git a/manifest.json b/manifest.json index 23ec0ffb6e..44ff07c46b 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "a4be311cb9d1e3697cc2760399d7c82144d4136dda714a2da14db87ebac3fea8", ".modelhub_state/recent_outcomes.jsonl": "b65a8637809936e8d8672436bc65a6880a573622f141f051aadc1337d9a18235", ".modelhub_state/recovery_active_tasks.jsonl": "3b7485a015392c7cac8a6de1894c65d732acc3a999bdedebea70be2540d9960e", - ".modelhub_state/recovery_intents.jsonl": "71999d06f6271d3143d791ec8bf716deb8368c9ae3e2b947a83bd925b490e13a", - ".modelhub_state/routing_intelligence.json": "03777e92ece2eacf748dd5af2a7710fe81773ac62e10e9d6e9965d2d2eec7aa8", + ".modelhub_state/recovery_intents.jsonl": "d1ba8192e38dcd4b4fd17776fa456d3c3a56ceb88f489cdc69da4606ec43a900", + ".modelhub_state/routing_intelligence.json": "0ce37d579648c84da0584cdbf5d3c5a51c6a6b51120af752628869ebd02f63e5", ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799", ".modelhub_state/worker_crashes.jsonl": "ccd40ad86ab5068ea1c3520a48fa733cf2e4b357ae5abb95ff00728d5d1b5487", - "ledger/submissions.jsonl": "308cdd0a5a1f4431c6451da2018ea0f84375c5e987adce3481a127f26edd70a0", - "outcomes/submissions.jsonl": "8b34ab17516c2737adaeb3bb2652848001a8014c124fe4ce85d1b6956d6d1745" + "ledger/submissions.jsonl": "62707b00307346d69e5865c59dee486272e9f8706beb68f77ee670f2a47a7afb", + "outcomes/submissions.jsonl": "316c67055a79fa55f7628506a84634693219347d9f4e315ad05e2810b04cfc7c" }, - "generation": 16549, - "phase": "intent", + "generation": 16550, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-26T12:46:23.576190+00:00", + "updatedAt": "2026-09-26T12:47:10.654949+00:00", "writerId": "08206cb1993a433e83f1d3e297db2d2e" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 9c46c12376..a109271185 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -839,3 +839,4 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-26T08:18:32.495861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5097281", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "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": 17593027563}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-26T11:27:31.250241+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5099581", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "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": 17593027563}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-26T11:43:40.248293+00:00", "targetGpu": "Vastai_va16", "taskId": "5099879", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "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": 19310889023, "modelscopeLicense": "other", "modelscopeParams": 5321729392, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310895273}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-26T12:47:09.108765+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5100778", "taskType": "text-generation", "verifyResult": null}