diff --git a/.modelhub_state/account_capacity.json b/.modelhub_state/account_capacity.json index fa36df7f5c..5f5fd32805 100644 --- a/.modelhub_state/account_capacity.json +++ b/.modelhub_state/account_capacity.json @@ -26,7 +26,7 @@ }, "b940824e4299693749aa": { "accountIndex": 6, - "knownCap": 4 + "knownCap": 5 }, "bc10735ccf9c93d0bc23": { "accountIndex": 12, @@ -49,6 +49,6 @@ "knownCap": 4 } }, - "updatedAt": "2026-10-21T13:05:07.734114+00:00", + "updatedAt": "2026-10-21T13:16:58.237893+00:00", "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 5c45be6b8a..168780cb64 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3669,18 +3669,18 @@ {"batchId": "ac919173e9b549668e5f79d4d4154344", "completedAt": "2026-10-21T12:05:07.909597+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:05:05.603070+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e466b3bec74f453eb1ee33b1b9ab4f6a", "lastModified": "2026-10-19T16:26:03+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-21T13:15:17.994527+00:00", "repoId": "cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5694040", "taskType": "text-generation"} {"batchId": "1298d3044c5d4b4595a39868082d85ea", "completedAt": "2026-10-21T12:36:30.480397+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:36:27.987113+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ea6347a88beb4f91afccb8b667774938", "lastModified": "2026-10-19T18:17:12+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "reason": null, "reconciledAt": "2026-10-21T13:15:17.995461+00:00", "repoId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5694581", "taskType": "text-generation"} {"batchId": "0a2e698e3d154068826f68964f7a3306", "completedAt": "2026-10-21T13:05:09.112909+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:05:06.402345+00:00", "framework": "vllm_tokenizer_patch", "intentId": "51e57abb336145669dc86bd20f5c8436", "lastModified": "2026-10-20T08:50:37+00:00", "modelAddress": "https://modelscope.cn/models/Haodong07/Qwen3-32B-TwinQuant-W4A4", "reason": null, "reconciledAt": "2026-10-21T13:15:17.997298+00:00", "repoId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5694815", "taskType": "text-generation"} -{"batchId": "8217688bd3674fada06876bba8c42aa3", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.912916+00:00", "framework": "vllm_tokenizer_patch", "intentId": "584debb2c1c943f1a8f18c3b48fe8429", "lastModified": "2026-10-19T17:09:46+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "repoId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} -{"batchId": "8217688bd3674fada06876bba8c42aa3", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913019+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e3242d6073454a04a56f0817f0ec1b3e", "lastModified": "2026-10-19T18:03:45+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "repoId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} -{"batchId": "8217688bd3674fada06876bba8c42aa3", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913067+00:00", "framework": "vllm_tokenizer_patch", "intentId": "58def36adf844796a5b4534f2db118fa", "lastModified": "2026-10-19T07:00:41+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-8B-W8A8", "repoId": "iluvatar-corex/Qwen3-8B-W8A8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} -{"batchId": "8217688bd3674fada06876bba8c42aa3", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913112+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f162bf84b2854c12ac400f35bdc655ff", "lastModified": "2026-10-19T07:29:23+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-14B-W8A8", "repoId": "iluvatar-corex/Qwen3-14B-W8A8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} -{"batchId": "8217688bd3674fada06876bba8c42aa3", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913155+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2cd7f353b95346539c7aa2706b0a5dcf", "lastModified": "2026-10-19T17:23:16+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "repoId": "cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} -{"batchId": "8217688bd3674fada06876bba8c42aa3", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913215+00:00", "framework": "vllm_tokenizer_patch", "intentId": "612e1c24ebb64b8a992096732deb5f6a", "lastModified": "2026-10-19T18:03:21+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "repoId": "cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} -{"batchId": "8217688bd3674fada06876bba8c42aa3", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913259+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a266ef4f49624a9694e85cbb631275cc", "lastModified": "2026-10-21T12:17:17+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B", "repoId": "LiquidAI/LFM2.5-24B-A2B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} -{"batchId": "8217688bd3674fada06876bba8c42aa3", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913301+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e01cca7c4fdd476990c8c18b68b1ab73", "lastModified": "2026-10-19T18:55:19+00:00", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-2.1-FP8-dynamic", "repoId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} -{"batchId": "8217688bd3674fada06876bba8c42aa3", "configFingerprint": "6227ad7464202af2fd72ed7ba47d960a6db14697bf850d85ff2e90b31777e3a8", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913343+00:00", "framework": "llamacpp", "intentId": "940fd658607748c0a4e1e44100ad3b8a", "lastModified": "2026-10-21T03:15:59+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.6-4B-GGUF", "repoId": "XHToken/Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "8217688bd3674fada06876bba8c42aa3", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913405+00:00", "framework": "llamacpp", "intentId": "c3883ec779894178bb60f7e6e6eb0d16", "lastModified": "2026-10-20T13:54:35+00:00", "modelAddress": "https://modelscope.cn/models/incoai/Muse-Glimmer-30B-DFlash2-GGUF", "repoId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "8217688bd3674fada06876bba8c42aa3", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913462+00:00", "framework": "llamacpp", "intentId": "d150af2c94744688b577db655d833605", "lastModified": "2026-10-20T05:58:12+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "repoId": "OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "8217688bd3674fada06876bba8c42aa3", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913516+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8a49d72cf3ec4c9690e5af078885ad5a", "lastModified": "2026-10-19T16:59:08+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cpatonn-mirror/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417198+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913155+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2cd7f353b95346539c7aa2706b0a5dcf", "lastModified": "2026-10-19T17:23:16+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "reason": null, "repoId": "cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "MetaX_c-500", "taskId": "5695060", "taskType": "text-generation"} +{"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417219+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913516+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8a49d72cf3ec4c9690e5af078885ad5a", "repoId": "cpatonn-mirror/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417216+00:00", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913462+00:00", "framework": "llamacpp", "intentId": "d150af2c94744688b577db655d833605", "repoId": "OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417213+00:00", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913405+00:00", "framework": "llamacpp", "intentId": "c3883ec779894178bb60f7e6e6eb0d16", "repoId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417210+00:00", "configFingerprint": "6227ad7464202af2fd72ed7ba47d960a6db14697bf850d85ff2e90b31777e3a8", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913343+00:00", "framework": "llamacpp", "intentId": "940fd658607748c0a4e1e44100ad3b8a", "repoId": "XHToken/Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417207+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913301+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e01cca7c4fdd476990c8c18b68b1ab73", "repoId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} +{"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417204+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913259+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a266ef4f49624a9694e85cbb631275cc", "repoId": "LiquidAI/LFM2.5-24B-A2B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} +{"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417202+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913215+00:00", "framework": "vllm_tokenizer_patch", "intentId": "612e1c24ebb64b8a992096732deb5f6a", "repoId": "cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} +{"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417195+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913112+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f162bf84b2854c12ac400f35bdc655ff", "repoId": "iluvatar-corex/Qwen3-14B-W8A8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} +{"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417190+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913067+00:00", "framework": "vllm_tokenizer_patch", "intentId": "58def36adf844796a5b4534f2db118fa", "repoId": "iluvatar-corex/Qwen3-8B-W8A8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} +{"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417175+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913019+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e3242d6073454a04a56f0817f0ec1b3e", "repoId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} +{"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417156+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.912916+00:00", "framework": "vllm_tokenizer_patch", "intentId": "584debb2c1c943f1a8f18c3b48fe8429", "repoId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} {"batchId": "57a51d2edb184f2f91a7740a1a24d2a4", "completedAt": "2026-10-21T13:15:15.577224+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:15:12.953923+00:00", "framework": "vllm_tokenizer_patch", "intentId": "63393243e1ed466ea0426720396c2004", "repoId": "cpatonn-mirror/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "57a51d2edb184f2f91a7740a1a24d2a4", "completedAt": "2026-10-21T13:15:15.577219+00:00", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:15:12.953869+00:00", "framework": "llamacpp", "intentId": "a59634b93564467d9624fb7d81dcf296", "repoId": "OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "57a51d2edb184f2f91a7740a1a24d2a4", "completedAt": "2026-10-21T13:15:15.577215+00:00", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:15:12.953813+00:00", "framework": "llamacpp", "intentId": "81319fcd579b4804a8f24443a19d76ab", "repoId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} @@ -3970,14 +3970,3 @@ {"batchId": "35af936a8ee941e98239f7fec794c677", "completedAt": "2026-10-21T12:42:56.905884+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:42:54.247690+00:00", "framework": "vllm_tokenizer_patch", "intentId": "aade49bd263e4e41a10265d66c4de5d3", "repoId": "iluvatar-corex/Qwen3-14B-W8A8", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "35af936a8ee941e98239f7fec794c677", "completedAt": "2026-10-21T12:42:56.905881+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:42:54.247638+00:00", "framework": "vllm_tokenizer_patch", "intentId": "992e2462928f4d23a33b0ad0aa6e2754", "repoId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "35af936a8ee941e98239f7fec794c677", "completedAt": "2026-10-21T12:42:56.905878+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:42:54.247583+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b70862a1d2494f95a0193a2affda3187", "repoId": "cpatonn-mirror/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "35af936a8ee941e98239f7fec794c677", "completedAt": "2026-10-21T12:42:56.905875+00:00", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:42:54.247526+00:00", "framework": "llamacpp", "intentId": "b452682954ec466ab7dedb77fd96641a", "repoId": "OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "35af936a8ee941e98239f7fec794c677", "completedAt": "2026-10-21T12:42:56.905871+00:00", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:42:54.247443+00:00", "framework": "llamacpp", "intentId": "ec342374fec24262836d7ebb60839f8d", "repoId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "35af936a8ee941e98239f7fec794c677", "completedAt": "2026-10-21T12:42:56.905852+00:00", "configFingerprint": "6227ad7464202af2fd72ed7ba47d960a6db14697bf850d85ff2e90b31777e3a8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:42:54.247322+00:00", "framework": "llamacpp", "intentId": "5c9e96b7a9654539960207c7c42d29ba", "repoId": "XHToken/Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "fdaadc6266d747c28f971b94db525b54", "completedAt": "2026-10-21T12:41:07.867369+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:41:05.187918+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0fd57408bc1245eb954e4b881a1b8c93", "repoId": "mlx-community/Qwen3.6-27B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "fdaadc6266d747c28f971b94db525b54", "completedAt": "2026-10-21T12:41:07.867366+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:41:05.187849+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0e13935a629449f8ab5cff7b4be962a4", "repoId": "cyankiwi/GLM-4.7-Flash-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "fdaadc6266d747c28f971b94db525b54", "completedAt": "2026-10-21T12:41:07.867363+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:41:05.187760+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4e858f986b3c46f6baedf97acaa0cf07", "repoId": "cyankiwi/Agents-A1-AWQ-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "fdaadc6266d747c28f971b94db525b54", "completedAt": "2026-10-21T12:41:07.867360+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:41:05.187671+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6ba0ac407bb54bea813e2f3fac4c6e79", "repoId": "StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "fdaadc6266d747c28f971b94db525b54", "completedAt": "2026-10-21T12:41:07.867357+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:41:05.187586+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8836059a0d5b442f9072c58ebc0469cc", "repoId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "fdaadc6266d747c28f971b94db525b54", "completedAt": "2026-10-21T12:41:07.867354+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:41:05.187501+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5af82bde87a4483cb84095642aa86fe9", "repoId": "cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "fdaadc6266d747c28f971b94db525b54", "completedAt": "2026-10-21T12:41:07.867351+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:41:05.187415+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f454f1025fe1457ca55f4623823548b2", "repoId": "iluvatar-corex/Qwen3-14B-W8A8", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "fdaadc6266d747c28f971b94db525b54", "completedAt": "2026-10-21T12:41:07.867348+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:41:05.187329+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4ba4b9b73ab445188070b439fb39616c", "repoId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 36c4a6b388..673d5d2fc3 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 3807 + "unified_success_first": 3808 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 36, @@ -29,7 +29,7 @@ "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 335, "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 98, "text-generation|MetaX_c-500|vllm": 138, - "text-generation|MetaX_c-500|vllm_tokenizer_patch": 124, + "text-generation|MetaX_c-500|vllm_tokenizer_patch": 125, "text-generation|Mthreads_s4000|llamacpp": 30, "text-generation|Mthreads_s4000|vllm": 195, "text-generation|Sunrise_pt-200-x1|vllm": 103, @@ -39,8 +39,8 @@ "text-generation|hygon_k100-ai|vllm": 35, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 238 }, - "acceptedSinceRefresh": 3807, - "acceptedTotal": 3807, - "generatedAt": "2026-10-21T13:15:15.441329+00:00", + "acceptedSinceRefresh": 3808, + "acceptedTotal": 3808, + "generatedAt": "2026-10-21T13:16:59.340803+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 4f94ff53b0..dff320156f 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1235,3 +1235,4 @@ {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XingChen-AGI/Xing4.0-29B-A4B", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "submitTime": "2026-10-13T12:52:58.552750+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5512698", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/XingChen-AGI/Xing4.0-29B-A4B", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "submitTime": "2026-10-13T13:12:18.147765+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5513114", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/DavidAU/DarkSapling-V2-Ultra-Quality-7B-GGUF", "modelId": "DavidAU/DarkSapling-V2-Ultra-Quality-7B-GGUF", "submitTime": "2026-10-15T20:46:16.830124+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5569369", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "modelId": "cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "submitTime": "2026-10-21T13:16:58.055588+00:00", "targetGpu": "MetaX_c-500", "taskId": "5695060", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} diff --git a/manifest.json b/manifest.json index eab4d0384a..18f1329270 100644 --- a/manifest.json +++ b/manifest.json @@ -1,7 +1,7 @@ { "agentVersion": "2026.09.04.4", "checksums": { - ".modelhub_state/account_capacity.json": "8d27a79f6e05518c068a45b13649c30e3299bea9ef3561258a1512f204280919", + ".modelhub_state/account_capacity.json": "0de860a802603835f7f8d44e221dce9057511c61dec1b2c8c94713e0e3fe8e55", ".modelhub_state/architecture_compatibility_blacklist.json": "c996a179f2ce61b52ee3e26dbd0daf1db44e8db73a30944bf5ef2ea98c182ee6", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/market_intelligence.json": "2af54507fdb6817a0d948ac4bb16e376a83c804634f8ac86b388d3cfeb6fb8b7", @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "faba403bbf86f519f695408e5951e34fcd78a468ec45cf54e0d557540f7c963b", ".modelhub_state/recent_outcomes.jsonl": "34964a2369c81d37ca8f7001745b57b669949fff2bd0bf028721300b6868a6b8", ".modelhub_state/recovery_active_tasks.jsonl": "acfc44431760fc5d82e6296014df05ff27ca6c67457414eb1a07f0480e696232", - ".modelhub_state/recovery_intents.jsonl": "14645a2a3578672b6a88dfb7999cdbe2535048d511c1ab491d9f2c9a901f8e87", - ".modelhub_state/routing_intelligence.json": "2ad571b3ac702fa621c4d28909327f3167e7c4937fb279dac664ec39995203cf", + ".modelhub_state/recovery_intents.jsonl": "30be24d58a3f7c4765667e3ef90b7d72d09fa404e9d5ac302c5f0d741702c99d", + ".modelhub_state/routing_intelligence.json": "e2b1782327da11b4e10d4d5d6ff2aca6e5f79d92dbedf90aaf816b2cd9479e72", ".modelhub_state/submission_exclusions.jsonl": "07b0cf531e208c0d6ecfffb156a0cb39a09636bee94976f2a8a2e3b767cf06cc", ".modelhub_state/worker_crashes.jsonl": "d46c42c2991f2fda703c2ba17f2b6a21afa8e1453bf67666f1bc0ff3bb99e2e9", - "ledger/submissions.jsonl": "992d96ee09b280fc59439719f64417de42c98e435915c9d4b6728dd19593a4af", - "outcomes/submissions.jsonl": "20b1966acfe5741847a1a2b26142f04004723cc2911921c95862b0d9e2271abc" + "ledger/submissions.jsonl": "e4f0a8d9c7ad990dba9566d131c9707257c03fd25ec50495eb16a24a916fb98f", + "outcomes/submissions.jsonl": "dde2401cb9674d13d5436dd41b4981ed809b6720119096dd6584c998b1fcf1f4" }, - "generation": 26964, - "phase": "intent", + "generation": 26965, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-10-21T13:16:57.086505+00:00", + "updatedAt": "2026-10-21T13:16:59.589854+00:00", "writerId": "f9d6ac09a4c14ca19fc241d193853c55" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 8d22708b2c..1ad5f63372 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1095,3 +1095,4 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064333187, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 33064333187}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T12:05:06.542231+00:00", "targetGpu": "MetaX_c-500", "taskId": "5694040", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459873078, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3459873078}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T12:36:29.041842+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5694581", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25339204672, "estimatedRequiredGiB": 28.332, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25350742978, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22705296512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25350742978}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T13:05:07.628503+00:00", "targetGpu": "MetaX_c-500", "taskId": "5694815", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26166907992, "estimatedRequiredGiB": 29.255, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 26176736582, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26176736582}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T13:16:58.055588+00:00", "targetGpu": "MetaX_c-500", "taskId": "5695060", "taskType": "text-generation", "verifyResult": null}