diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 43a5246b..042bd573 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -723,8 +723,8 @@ {"batchId": "5c6a74addbaf45d6ae8bd4e69e82afff", "completedAt": "2026-09-13T19:22:53.119239+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-13T19:22:44.823053+00:00", "framework": "vllm", "intentId": "5d2f42c46dfe4b9f864337057a010ef2", "lastModified": "2026-09-04T07:05:18+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "reason": null, "reconciledAt": "2026-09-14T06:48:16.286339+00:00", "repoId": "XHToken/Spark-X2.5-4B-INT8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4834315", "taskType": "text-generation"} {"batchId": "e51a97ee7fdd4fb0bf7eff72a1a57bc1", "completedAt": "2026-09-13T22:17:52.834549+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-13T22:17:42.933426+00:00", "framework": "vllm-mlu", "intentId": "7a593db872ff46b6880421b142399e5f", "lastModified": "2026-09-04T07:05:18+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "reason": null, "reconciledAt": "2026-09-14T06:48:16.287692+00:00", "repoId": "XHToken/Spark-X2.5-4B-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4836986", "taskType": "text-generation"} {"batchId": "6006db5672e04f86aeec227ac92ad90d", "completedAt": "2026-09-14T06:48:14.353571+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-14T06:47:58.931898+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2997d9211e83440eb5a8086dad96195f", "lastModified": "2026-09-14T06:33:18+00:00", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-35B-A3B-preview", "reason": null, "reconciledAt": "2026-09-14T06:48:16.287688+00:00", "repoId": "Edge0/Edge0-35B-A3B-preview", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4844610", "taskType": "text-generation"} -{"batchId": "3ee003fbc54e423c8b22f2a360ee892a", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-14T06:58:37.280146+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b9d1e0d567fc4107b61bda9eeaadf7f1", "lastModified": "2026-09-14T05:50:12+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw", "repoId": "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "3ee003fbc54e423c8b22f2a360ee892a", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-14T06:58:37.280265+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ef66e95694204e25b3604e1e0b652367", "lastModified": "2026-08-12T03:35:07+00:00", "modelAddress": "https://modelscope.cn/models/huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "repoId": "huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "3ee003fbc54e423c8b22f2a360ee892a", "completedAt": "2026-09-14T06:58:51.649715+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-14T06:58:37.280146+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b9d1e0d567fc4107b61bda9eeaadf7f1", "lastModified": "2026-09-14T05:50:12+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw", "reason": null, "repoId": "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4844797", "taskType": "text-generation"} +{"batchId": "3ee003fbc54e423c8b22f2a360ee892a", "completedAt": "2026-09-14T06:58:51.649726+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-14T06:58:37.280265+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ef66e95694204e25b3604e1e0b652367", "lastModified": "2026-08-12T03:35:07+00:00", "modelAddress": "https://modelscope.cn/models/huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "reason": null, "repoId": "huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4844799", "taskType": "text-generation"} {"batchId": "83639d5151dd4bb78879458f9850c53a", "completedAt": "2026-09-14T06:07:56.622377+00:00", "configFingerprint": "e4588bdbccc377f0f7599581ea0752e64b81eda54f82b575b6aaa81c27ce2e73", "configSource": "modelhub_live", "createdAt": "2026-09-14T06:07:48.751836+00:00", "framework": "llamacpp", "intentId": "35fd7d8028f54640b4d005111704edc0", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "9ea43510e22a43e9991959f19dd0f4a2", "completedAt": "2026-09-13T12:43:37.101071+00:00", "configFingerprint": "7d273c6d9a11c4e826d64fc44d3ae14d805bd3b1e6e663d4dd0b45567cfc5e3f", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:43:27.207464+00:00", "framework": "llamacpp", "intentId": "ab083753c716462fbb8b0529ac182658", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "9370c3290d2242cebbdd1924870f426b", "completedAt": "2026-09-13T12:41:31.618354+00:00", "configFingerprint": "d7cf4e4fcae21f022bbcb9f71b3bb0ab37d6331cf8fd1cd3ad4ba75043690051", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:41:17.857077+00:00", "framework": "llamacpp", "intentId": "8c62b06728694cd9b6f7c5c378f53285", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 2d13642b..eaca7914 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 858 + "unified_success_first": 860 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 12, @@ -16,7 +16,7 @@ "text-generation|Iluvatar_bi-150|llamacpp": 12, "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 66, "text-generation|Iluvatar_mrv-100|vllm": 40, - "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 102, + "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 104, "text-generation|MetaX_c-500|vllm": 90, "text-generation|Mthreads_s4000|llamacpp": 12, "text-generation|Mthreads_s4000|vllm": 64, @@ -26,8 +26,8 @@ "text-generation|hygon_k100-ai|llamacpp": 12, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 48 }, - "acceptedSinceRefresh": 858, - "acceptedTotal": 858, - "generatedAt": "2026-09-14T06:48:14.320460+00:00", + "acceptedSinceRefresh": 860, + "acceptedTotal": 860, + "generatedAt": "2026-09-14T06:58:51.616223+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 3ebb61fb..812400e1 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -781,3 +781,5 @@ {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-08T15:58:20.200513+00:00", "targetGpu": "Vastai_va16", "taskId": "4722293", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "modelId": "OpenBMB/BitCPM-CANN-8B", "submitTime": "2026-09-09T12:30:12.314907+00:00", "targetGpu": "Vastai_va16", "taskId": "4740401", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "submitTime": "2026-09-09T21:08:22.097030+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746441", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw", "modelId": "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw", "submitTime": "2026-09-14T06:58:38.810772+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844797", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "modelId": "huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "submitTime": "2026-09-14T06:58:38.815931+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844799", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} diff --git a/manifest.json b/manifest.json index 9eda34fb..3a23626e 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "0ca25e7a552999a61b0e5c18fc5c08134dd7fe9caf89eaa601a60afcccac2b45", ".modelhub_state/recent_outcomes.jsonl": "b2fd8ae4b8d3c09d6c62f53601835a4413a1621536453f4db1a2133081d6195c", ".modelhub_state/recovery_active_tasks.jsonl": "53e020fc51fd474ae618620cab0ea12dfb386f5c3f5fb454cddda31f8c03e038", - ".modelhub_state/recovery_intents.jsonl": "1b06061fa271994ade657e45fa28165337b9f3f9817b986035588e1e210743e7", - ".modelhub_state/routing_intelligence.json": "4dfb202ad8362a449c659918d0c81f33fc95f14fa96fad205abf3e1a288f4060", + ".modelhub_state/recovery_intents.jsonl": "f6f9d3c9129faf8af1501066596b634c9659b1a0b0731d0aeccc4c6a63435d0a", + ".modelhub_state/routing_intelligence.json": "e3b400bab2d262c6fb17fe934921f6a1410f10211e52161299f69c02505d9020", ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552", ".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad", - "ledger/submissions.jsonl": "e67800038248f9223d75fae0d37ac7cf7ece7b7b1d349d4a0b4b97986bcb48a5", - "outcomes/submissions.jsonl": "ea57bbfbe5500798de78e1fecd4b5cea96c676ee44e6af9d95fa61da00501af8" + "ledger/submissions.jsonl": "000d1693f261c0f105214fbb61e7169b72cf92e94a67752a26b510fd202a6222", + "outcomes/submissions.jsonl": "f67c4bb9923da1f13d0dc8ad37280a10583d0e61527c4d02ebca476efbe36c64" }, - "generation": 7057, - "phase": "intent", + "generation": 7058, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-14T06:58:37.364191+00:00", + "updatedAt": "2026-09-14T06:58:51.729962+00:00", "writerId": "69701e73196b4ac2b3fad0f412335168" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 9f0ac4f3..8c61906d 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -623,3 +623,5 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-14T03:29:33.013591+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T19:22:45.622511+00:00", "targetGpu": "Biren_166m", "taskId": "4834315", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-14T06:17:54.916608+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T22:17:43.666489+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4836986", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T06:48:00.583349+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4844610", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw", "modelProfile": {"architectures": ["Qwen4ExpForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 32000153976, "estimatedRequiredGiB": 96.509, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen4_exp", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 14924740499, "modelscopeTags": ["license:other", "model_type:qwen4_exp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen4_exp", "custom_tag:moe", "custom_tag:sparse-attention", "custom_tag:ngram-embedding", "custom_tag:imatrix"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 86355120331}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T06:58:38.810772+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844797", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903777808, "estimatedRequiredGiB": 80.381, "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": 71923892164, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:abliterated", "custom_tag:uncensored", "custom_tag:huihui", "custom_tag:offensive-security", "custom_tag:pentesting", "custom_tag:tool-calling", "custom_tag:cyberstrike", "custom_tag:qwen3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 71923892164}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T06:58:38.815931+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844799", "taskType": "text-generation", "verifyResult": null}