diff --git a/.modelhub_state/account_capacity.json b/.modelhub_state/account_capacity.json index 5f5fd32805..3365e2b5eb 100644 --- a/.modelhub_state/account_capacity.json +++ b/.modelhub_state/account_capacity.json @@ -26,7 +26,7 @@ }, "b940824e4299693749aa": { "accountIndex": 6, - "knownCap": 5 + "knownCap": 6 }, "bc10735ccf9c93d0bc23": { "accountIndex": 12, @@ -49,6 +49,6 @@ "knownCap": 4 } }, - "updatedAt": "2026-10-21T13:16:58.237893+00:00", + "updatedAt": "2026-10-21T13:17:59.934238+00:00", "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 7413e205dd..bd96d75db8 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3670,18 +3670,18 @@ {"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": "2026-10-21T13:17:04.090647+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": "2026-10-21T13:17:04.089752+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", "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, "reconciledAt": "2026-10-21T13:17:04.089308+00:00", "repoId": "cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5695060", "taskType": "text-generation"} -{"batchId": "4b6c1b110509451a837f2a82ede97acd", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499128+00:00", "framework": "vllm_tokenizer_patch", "intentId": "12f7214ec155413b91d8aee1ef643158", "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": "4b6c1b110509451a837f2a82ede97acd", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499243+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4126b4b567044a68823ec88f6fef8ca3", "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": "4b6c1b110509451a837f2a82ede97acd", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499292+00:00", "framework": "vllm_tokenizer_patch", "intentId": "06f72a9215854d908bd0e8a00f8513f7", "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": "4b6c1b110509451a837f2a82ede97acd", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499335+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5a34f0a0c742407ab303a5ff22d0ad33", "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": "4b6c1b110509451a837f2a82ede97acd", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499378+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6b130188ee274275b86fe7380373959a", "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": "4b6c1b110509451a837f2a82ede97acd", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499420+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4cec4376c34e432fb5a0923987e069f7", "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": "4b6c1b110509451a837f2a82ede97acd", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499462+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6b505e4a651d401e9690731b00a76321", "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": "4b6c1b110509451a837f2a82ede97acd", "configFingerprint": "6227ad7464202af2fd72ed7ba47d960a6db14697bf850d85ff2e90b31777e3a8", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499503+00:00", "framework": "llamacpp", "intentId": "60124505fb3d4b18b9a7c7b4a4c46306", "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": "4b6c1b110509451a837f2a82ede97acd", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499563+00:00", "framework": "llamacpp", "intentId": "5593d569b32e432fb70db947847fa149", "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": "4b6c1b110509451a837f2a82ede97acd", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499619+00:00", "framework": "llamacpp", "intentId": "defa3d210ff24015868e0b21a06511d6", "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": "4b6c1b110509451a837f2a82ede97acd", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499672+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fc867beb75194178b5b9ebee80013d4a", "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": "4b6c1b110509451a837f2a82ede97acd", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499726+00:00", "framework": "vllm_tokenizer_patch", "intentId": "915bf10155574e2bb292b5702903066d", "lastModified": "2026-10-19T07:32:17+00:00", "modelAddress": "https://modelscope.cn/models/StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "repoId": "StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244788+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499243+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4126b4b567044a68823ec88f6fef8ca3", "lastModified": "2026-10-19T18:03:45+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "reason": null, "repoId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "MetaX_c-500", "taskId": "5695068", "taskType": "text-generation"} +{"batchId": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244829+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499726+00:00", "framework": "vllm_tokenizer_patch", "intentId": "915bf10155574e2bb292b5702903066d", "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": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244826+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499672+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fc867beb75194178b5b9ebee80013d4a", "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": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244822+00:00", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499619+00:00", "framework": "llamacpp", "intentId": "defa3d210ff24015868e0b21a06511d6", "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": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244818+00:00", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499563+00:00", "framework": "llamacpp", "intentId": "5593d569b32e432fb70db947847fa149", "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": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244814+00:00", "configFingerprint": "6227ad7464202af2fd72ed7ba47d960a6db14697bf850d85ff2e90b31777e3a8", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499503+00:00", "framework": "llamacpp", "intentId": "60124505fb3d4b18b9a7c7b4a4c46306", "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": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244810+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499462+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6b505e4a651d401e9690731b00a76321", "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": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244806+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499420+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4cec4376c34e432fb5a0923987e069f7", "repoId": "LiquidAI/LFM2.5-24B-A2B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} +{"batchId": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244802+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499378+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6b130188ee274275b86fe7380373959a", "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": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244798+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499335+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5a34f0a0c742407ab303a5ff22d0ad33", "repoId": "iluvatar-corex/Qwen3-14B-W8A8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} +{"batchId": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244793+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499292+00:00", "framework": "vllm_tokenizer_patch", "intentId": "06f72a9215854d908bd0e8a00f8513f7", "repoId": "iluvatar-corex/Qwen3-8B-W8A8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} +{"batchId": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244766+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499128+00:00", "framework": "vllm_tokenizer_patch", "intentId": "12f7214ec155413b91d8aee1ef643158", "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": "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"} @@ -3971,14 +3971,3 @@ {"batchId": "f055729a67024e8b96397e62aaa35720", "completedAt": "2026-10-21T12:44:41.868821+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:44:38.525398+00:00", "framework": "vllm_tokenizer_patch", "intentId": "61e64396bbd14666a9443dfc65bf4cc7", "repoId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f055729a67024e8b96397e62aaa35720", "completedAt": "2026-10-21T12:44:41.868818+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:44:38.525345+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a10ddc5e51d74af49bec44c954401436", "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": "f055729a67024e8b96397e62aaa35720", "completedAt": "2026-10-21T12:44:41.868815+00:00", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:44:38.525290+00:00", "framework": "llamacpp", "intentId": "37b633330a914e628ac00dc3b9fb1acb", "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": "f055729a67024e8b96397e62aaa35720", "completedAt": "2026-10-21T12:44:41.868810+00:00", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:44:38.525229+00:00", "framework": "llamacpp", "intentId": "746342be5fd74fd992643d541c1e0913", "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": "f055729a67024e8b96397e62aaa35720", "completedAt": "2026-10-21T12:44:41.868791+00:00", "configFingerprint": "6227ad7464202af2fd72ed7ba47d960a6db14697bf850d85ff2e90b31777e3a8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:44:38.525111+00:00", "framework": "llamacpp", "intentId": "c1b4b8068d5c472598705b27e00599e4", "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": "35af936a8ee941e98239f7fec794c677", "completedAt": "2026-10-21T12:42:56.905902+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:42:54.248039+00:00", "framework": "vllm_tokenizer_patch", "intentId": "daa00667cd2e4cf0a15cea8a63116501", "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": "35af936a8ee941e98239f7fec794c677", "completedAt": "2026-10-21T12:42:56.905899+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:42:54.247998+00:00", "framework": "vllm_tokenizer_patch", "intentId": "573bc0a128164b4c8a3610241a2122b2", "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": "35af936a8ee941e98239f7fec794c677", "completedAt": "2026-10-21T12:42:56.905896+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:42:54.247908+00:00", "framework": "vllm_tokenizer_patch", "intentId": "da878fb6600f4290a615968600b6fd97", "repoId": "cyankiwi/Agents-A1-AWQ-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "35af936a8ee941e98239f7fec794c677", "completedAt": "2026-10-21T12:42:56.905893+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:42:54.247842+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a7312bc5e2ae4eed8cc0f493a3504648", "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": "35af936a8ee941e98239f7fec794c677", "completedAt": "2026-10-21T12:42:56.905890+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:42:54.247792+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f12a893dadc54770a7a2d5c37661e584", "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": "35af936a8ee941e98239f7fec794c677", "completedAt": "2026-10-21T12:42:56.905887+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:42:54.247741+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cc81743634a7492797bc7e3c9109afc9", "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": "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"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 673d5d2fc3..b9077e5f7c 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 3808 + "unified_success_first": 3809 }, "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": 125, + "text-generation|MetaX_c-500|vllm_tokenizer_patch": 126, "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": 3808, - "acceptedTotal": 3808, - "generatedAt": "2026-10-21T13:16:59.340803+00:00", + "acceptedSinceRefresh": 3809, + "acceptedTotal": 3809, + "generatedAt": "2026-10-21T13:18:01.125285+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 2887d544b7..abc5df5f4b 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/Seed-OSS-36B-Instruct-AWQ-4bit", "modelId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "submitTime": "2026-10-21T13:17:59.733260+00:00", "targetGpu": "MetaX_c-500", "taskId": "5695068", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} diff --git a/manifest.json b/manifest.json index 9c4283974d..67c73f7701 100644 --- a/manifest.json +++ b/manifest.json @@ -1,7 +1,7 @@ { "agentVersion": "2026.09.04.4", "checksums": { - ".modelhub_state/account_capacity.json": "0de860a802603835f7f8d44e221dce9057511c61dec1b2c8c94713e0e3fe8e55", + ".modelhub_state/account_capacity.json": "292c40b042e5820862eb4f392420a2f4d6ed8af11dd5f95a5f5ea60511053e15", ".modelhub_state/architecture_compatibility_blacklist.json": "7c7b3b48906cc17de166281ce7a2d803213952c37df83c2586528942bc440a90", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/market_intelligence.json": "8169d2641c0963ba3932f445253e98ff6e7233d15a1406c86fcc3005895d22a0", @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "faba403bbf86f519f695408e5951e34fcd78a468ec45cf54e0d557540f7c963b", ".modelhub_state/recent_outcomes.jsonl": "34964a2369c81d37ca8f7001745b57b669949fff2bd0bf028721300b6868a6b8", ".modelhub_state/recovery_active_tasks.jsonl": "f359a72e803ce6c03a66fc2cd9ebd28019f666dad6cc702df920ef6c7e9dc1a4", - ".modelhub_state/recovery_intents.jsonl": "708896e4ea72485b3888bc05c32afee3473c4f504342a68d6047535ec7b3160f", - ".modelhub_state/routing_intelligence.json": "e2b1782327da11b4e10d4d5d6ff2aca6e5f79d92dbedf90aaf816b2cd9479e72", + ".modelhub_state/recovery_intents.jsonl": "ee0f7490a33008b967ac659d8fd8a745fb5771e419e6f26e6c711604109045df", + ".modelhub_state/routing_intelligence.json": "e12fd518da670a53bb828613e10b61d322492e15d273aa4fef9b3b8d10470cdd", ".modelhub_state/submission_exclusions.jsonl": "07b0cf531e208c0d6ecfffb156a0cb39a09636bee94976f2a8a2e3b767cf06cc", ".modelhub_state/worker_crashes.jsonl": "d46c42c2991f2fda703c2ba17f2b6a21afa8e1453bf67666f1bc0ff3bb99e2e9", - "ledger/submissions.jsonl": "e79b51b9093d88536ab58c2bd31510157ef211207d03f418e3d4ed3143040a57", - "outcomes/submissions.jsonl": "dde2401cb9674d13d5436dd41b4981ed809b6720119096dd6584c998b1fcf1f4" + "ledger/submissions.jsonl": "f6f2b4dc6f80563e12b7459a54304f4afd8b749ae0c98aaf6fe53589a06070f9", + "outcomes/submissions.jsonl": "8bc85f54728c97942ec404e631b8c4bd15ce93c55d01d510a5d1ef4524427cdd" }, - "generation": 26967, - "phase": "intent", + "generation": 26968, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-10-21T13:17:58.676162+00:00", + "updatedAt": "2026-10-21T13:18:01.418544+00:00", "writerId": "f9d6ac09a4c14ca19fc241d193853c55" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 1ad5f63372..52c6e6a48c 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1096,3 +1096,4 @@ {"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} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["SeedOssForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21000825520, "estimatedRequiredGiB": 23.484, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "seed_oss", "modelscopeFileSize": 21013103805, "modelscopeLicense": "apache-2.0", "modelscopeParams": 36151104512, "modelscopeTags": ["license:apache-2.0", "model_type:seed_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 21013103805}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T13:17:59.733260+00:00", "targetGpu": "MetaX_c-500", "taskId": "5695068", "taskType": "text-generation", "verifyResult": null}