diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index c089d1fc..6ebf1db3 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -610,8 +610,8 @@ {"batchId": "86a0fddfa62f41c2a4d6758eded79ff4", "completedAt": "2026-09-10T05:56:06.407700+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-10T05:55:58.654349+00:00", "framework": "vllm", "intentId": "95f91086cc15476ca4cce1af77b6d3ac", "lastModified": "2026-09-10T05:36:14+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "reason": null, "reconciledAt": "2026-09-10T06:05:16.335964+00:00", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754067", "taskType": "text-generation"} {"batchId": "86a0fddfa62f41c2a4d6758eded79ff4", "completedAt": "2026-09-10T05:56:06.407702+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-10T05:55:58.654403+00:00", "framework": "vllm-patch-tokenizer", "intentId": "662b05f4f8744b168b694c17342e0d53", "lastModified": "2026-09-10T05:34:35+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "reason": null, "reconciledAt": "2026-09-10T06:05:16.336366+00:00", "repoId": "primitive-ai/Nex-N2.5-mini-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4754068", "taskType": "text-generation"} {"batchId": "4b290bbef2fc43bba9150558c6cf6475", "completedAt": "2026-09-10T06:03:44.056126+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:03:36.773834+00:00", "framework": "vllm", "intentId": "4db38e47d59a4a5f9df6353105f11896", "lastModified": "2026-08-11T14:42:47+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "reason": null, "reconciledAt": "2026-09-10T06:05:16.335167+00:00", "repoId": "BAAI/AREX-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754205", "taskType": "text-generation"} -{"batchId": "87f18eca7da24da89ad9b1e2bfaf6832", "configFingerprint": "37bac6ce21d60134ebaca4c6569bab1151fd62af1ad962effbf472bc8bdbafbc", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:11:10.765754+00:00", "framework": "llamacpp", "intentId": "cb4b0d3ad405447692f618fa153f1210", "lastModified": "2026-09-10T05:46:18+00:00", "modelAddress": "https://modelscope.cn/models/bartowski/MiniCPM5-2B-GGUF", "repoId": "bartowski/MiniCPM5-2B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "87f18eca7da24da89ad9b1e2bfaf6832", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:11:10.765856+00:00", "framework": "vllm_tokenizer_patch", "intentId": "575d3694806a4c8f9d34a407e05b5a13", "lastModified": "2026-09-10T05:57:11+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "87f18eca7da24da89ad9b1e2bfaf6832", "completedAt": "2026-09-10T06:11:21.275234+00:00", "configFingerprint": "37bac6ce21d60134ebaca4c6569bab1151fd62af1ad962effbf472bc8bdbafbc", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:11:10.765754+00:00", "framework": "llamacpp", "intentId": "cb4b0d3ad405447692f618fa153f1210", "lastModified": "2026-09-10T05:46:18+00:00", "modelAddress": "https://modelscope.cn/models/bartowski/MiniCPM5-2B-GGUF", "reason": null, "repoId": "bartowski/MiniCPM5-2B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4754342", "taskType": "text-generation"} +{"batchId": "87f18eca7da24da89ad9b1e2bfaf6832", "completedAt": "2026-09-10T06:11:21.275249+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-10T06:11:10.765856+00:00", "framework": "vllm_tokenizer_patch", "intentId": "575d3694806a4c8f9d34a407e05b5a13", "lastModified": "2026-09-10T05:57:11+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "reason": null, "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4754343", "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 76fcf1d9..626daec2 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,11 +1,11 @@ { "acceptedByCategory": { - "unified_success_first": 745 + "unified_success_first": 747 }, "acceptedByRoute": { - "text-generation|Ascend_910-b3|llamacpp": 8, + "text-generation|Ascend_910-b3|llamacpp": 9, "text-generation|Ascend_910-b3|vllm": 16, - "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 19, + "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 20, "text-generation|Ascend_910-b4|llamacpp": 6, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 27, "text-generation|Biren_166m|vllm": 45, @@ -25,8 +25,8 @@ "text-generation|hygon_k100-ai|llamacpp": 9, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 42 }, - "acceptedSinceRefresh": 745, - "acceptedTotal": 745, - "generatedAt": "2026-09-10T06:03:44.028998+00:00", + "acceptedSinceRefresh": 747, + "acceptedTotal": 747, + "generatedAt": "2026-09-10T06:11:21.246291+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 8ffc0da1..dda30576 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -706,3 +706,5 @@ {"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": "llamacpp", "modelAddress": "https://modelscope.cn/models/bartowski/MiniCPM5-2B-GGUF", "modelId": "bartowski/MiniCPM5-2B-GGUF", "submitTime": "2026-09-10T06:11:11.806743+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4754342", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T06:11:11.799771+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4754343", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} diff --git a/manifest.json b/manifest.json index ff00cabd..cc43a685 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99", ".modelhub_state/recent_outcomes.jsonl": "fe315011c870521f867a99cbaeb13ed5c634883c5f8fd597757b84e80cdc77b4", ".modelhub_state/recovery_active_tasks.jsonl": "98d6085d5cea77e8fe6a9884fb587dc72a819d709c4552bcc9a76ea2e8b162a8", - ".modelhub_state/recovery_intents.jsonl": "53795f77157ebe7a84f401e8bd57509943b71e758fb0c7b39a45b6d9b3902297", - ".modelhub_state/routing_intelligence.json": "f9ebf6b7b8ae06030c651e7942b7a357d8a2828edad8391c2935e2c435fcf497", + ".modelhub_state/recovery_intents.jsonl": "0ed1f817abe6df7d525e7480693e62770dff209e898aff4a240ea067fe839114", + ".modelhub_state/routing_intelligence.json": "2bcf282aca5e80c40fefce715a37522af02f158f738d7af3afbef7343ae646ef", ".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03", ".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76", - "ledger/submissions.jsonl": "f8c7284660af100fbfd1e800575e7f1036b4a56ca15236b7f07bff4420937641", - "outcomes/submissions.jsonl": "6cdac6e896b7a46d7840479a2688ba41eb22b6cee6da70c8283458e179ac94f8" + "ledger/submissions.jsonl": "c72ccf0648ba85294680724364679bb2274bf98a1b673753359e7a2de8e57102", + "outcomes/submissions.jsonl": "29667bd281b180064604bb17ff78893a76e2055febbf2f7cdd02daa83d33de5a" }, - "generation": 5001, - "phase": "intent", + "generation": 5002, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-10T06:11:10.908305+00:00", + "updatedAt": "2026-09-10T06:11:21.334917+00:00", "writerId": "58ff5dc2a2d64b119ad1e4560700f977" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 6cb00a2e..da673aec 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -576,3 +576,5 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "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": null, "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": "2026-09-10T05:55:59.435840+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754067", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "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": null, "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": "2026-09-10T05:55:59.437900+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754068", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T06:03:37.655467+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754205", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "37bac6ce21d60134ebaca4c6569bab1151fd62af1ad962effbf472bc8bdbafbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-10T06:11:11.806743+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4754342", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-10T06:11:11.799771+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4754343", "taskType": "text-generation", "verifyResult": null}