diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 673f1919..c10721dc 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -617,8 +617,8 @@ {"batchId": "0eba3fbd543f4c7ca0de173706074663", "completedAt": "2026-09-10T06:13:04.904305+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:12:56.217342+00:00", "framework": "vllm", "intentId": "c5ca6bcddcca4c4498a1d0c93f75b529", "lastModified": "2026-09-10T05:34:35+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "reason": null, "reconciledAt": "2026-09-10T06:29:04.406660+00:00", "repoId": "primitive-ai/Nex-N2.5-mini-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4754371", "taskType": "text-generation"} {"batchId": "8d1b53bc9ba9474ca3c99e943aabda33", "completedAt": "2026-09-10T06:29:02.476382+00:00", "configFingerprint": "9ee85a9702ae695242c8b5436b1b856292d4a16c2f839d36bf93fbe98fb66d4e", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:28:55.444531+00:00", "framework": "llamacpp", "intentId": "3ece1199138149888cbdee5d0236242f", "lastModified": "2026-09-10T05:46:18+00:00", "modelAddress": "https://modelscope.cn/models/bartowski/MiniCPM5-2B-GGUF", "reason": null, "reconciledAt": "2026-09-10T06:29:04.406855+00:00", "repoId": "bartowski/MiniCPM5-2B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4754660", "taskType": "text-generation"} {"batchId": "8d1b53bc9ba9474ca3c99e943aabda33", "completedAt": "2026-09-10T06:29:02.476392+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:28:55.444637+00:00", "framework": "vllm", "intentId": "14625abdfeca4e868e1155c3bda46498", "lastModified": "2026-09-10T05:57:11+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "reason": null, "reconciledAt": "2026-09-10T06:29:04.406263+00:00", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754659", "taskType": "text-generation"} -{"batchId": "94b34dbed880472e96fab53cf65df290", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:30:52.322384+00:00", "framework": "vllm-patch-tokenizer", "intentId": "b2d5c0fda9af4027b22a36525629d72b", "lastModified": "2026-09-10T05:31:36+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "94b34dbed880472e96fab53cf65df290", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:30:52.322478+00:00", "framework": "vllm-patch-tokenizer", "intentId": "98e27a19de9d4bd698236481614d1650", "lastModified": "2026-09-10T05:36:14+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} +{"batchId": "94b34dbed880472e96fab53cf65df290", "completedAt": "2026-09-10T06:30:59.219165+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:30:52.322384+00:00", "framework": "vllm-patch-tokenizer", "intentId": "b2d5c0fda9af4027b22a36525629d72b", "lastModified": "2026-09-10T05:31:36+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "reason": null, "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4754721", "taskType": "text-generation"} +{"batchId": "94b34dbed880472e96fab53cf65df290", "completedAt": "2026-09-10T06:30:59.219177+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:30:52.322478+00:00", "framework": "vllm-patch-tokenizer", "intentId": "98e27a19de9d4bd698236481614d1650", "lastModified": "2026-09-10T05:36:14+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "reason": null, "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4754722", "taskType": "text-generation"} {"batchId": "93abbd86b4564ff2b94a94e46d15997c", "completedAt": "2026-09-10T02:01:15.152981+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-10T02:01:07.997982+00:00", "framework": "vllm", "intentId": "f62de0b86d234667845793d4dabba8be", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"} {"batchId": "60b640169cee4eb6aeaf36aa752d68d4", "completedAt": "2026-09-09T21:08:33.584377+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-09T21:08:21.304731+00:00", "framework": "vllm_fix_tokenizer", "intentId": "31500eb429ef4b3cbc844e4096a6b5f6", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "395e59f0f1df48fcb2e0269b69d9bce5", "completedAt": "2026-09-09T16:24:21.684805+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-09T16:24:14.160686+00:00", "framework": "vllm", "intentId": "e2523fa4e63645688fd5e7c0c7c1a5d5", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index fcc43a0e..f04c9514 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 752 + "unified_success_first": 754 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 9, @@ -23,10 +23,10 @@ "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 50, "text-generation|Vastai_va16|vllm_fix_tokenizer": 34, "text-generation|hygon_k100-ai|llamacpp": 9, - "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 42 + "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 44 }, - "acceptedSinceRefresh": 752, - "acceptedTotal": 752, - "generatedAt": "2026-09-10T06:29:02.444480+00:00", + "acceptedSinceRefresh": 754, + "acceptedTotal": 754, + "generatedAt": "2026-09-10T06:30:59.187406+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 0c93017c..5f2eaf89 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -712,3 +712,5 @@ {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-08T06:46:11.934706+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712836", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-08T14:03:45.031522+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4720262", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} {"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-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-10T06:30:53.020882+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754721", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} +{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-10T06:30:53.025848+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754722", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} diff --git a/manifest.json b/manifest.json index 8fcf5043..cccc3212 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99", ".modelhub_state/recent_outcomes.jsonl": "0349f991e1e1669c358319e65ce6a7cbc1fca49287207bd1f03243519925cc61", ".modelhub_state/recovery_active_tasks.jsonl": "fdf9017dcace1417f50a3e0c57a5a462c18ea6b2807db20b66fcc5e5c8accbd1", - ".modelhub_state/recovery_intents.jsonl": "75d86ee27f7fdfbcf2bef6030a4ccdf09cbba4e3caeab8e6777a98f1778b6567", - ".modelhub_state/routing_intelligence.json": "e50bee49e6207e9c56dd2edc054ad3de86118505ec2ac86e9f353a32f42c5872", + ".modelhub_state/recovery_intents.jsonl": "a2d07b07fe60fac917434fc85ec1c719928bc0708578767594be20044c853b4f", + ".modelhub_state/routing_intelligence.json": "fa6d4c5a492c47d1b88098cbabca1f9fe662cc8b20179d7f0d2fdb724608b3ca", ".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03", ".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76", - "ledger/submissions.jsonl": "6e23ee06fa9bb4ece57899f4ecc8391ce776e7ea3d53980b537b82d08710b4e3", - "outcomes/submissions.jsonl": "f1edb378b33deb3d028d765713902d2954d339961bbaaa94d0999381dc8a8261" + "ledger/submissions.jsonl": "1ca50d71b15887797887b8960db759ec2f8f8923ded5df29a0106c95decadc5b", + "outcomes/submissions.jsonl": "e6b061cddf83f75ea9f43f8916381e16b61c0a8402ae2656bb6f83df34ac3b22" }, - "generation": 5015, - "phase": "intent", + "generation": 5016, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-10T06:30:52.436648+00:00", + "updatedAt": "2026-09-10T06:30:59.283720+00:00", "writerId": "58ff5dc2a2d64b119ad1e4560700f977" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index f839d232..5e53cdf8 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -581,3 +581,5 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T06:12:56.905628+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4754371", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9ee85a9702ae695242c8b5436b1b856292d4a16c2f839d36bf93fbe98fb66d4e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 36341551917, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T06:28:56.145522+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4754660", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T06:28:56.134725+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754659", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T06:30:53.020882+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754721", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T06:30:53.025848+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754722", "taskType": "text-generation", "verifyResult": null}