diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index e54c0140..e909058e 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -631,7 +631,7 @@ {"batchId": "f9e866c67cf14708a87905c2954924e8", "completedAt": "2026-09-10T07:12:35.485229+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-10T07:12:25.475137+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3e8d3bcf62af4f8cbc19db016bbdd397", "lastModified": "2026-08-11T14:42:47+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "reason": null, "reconciledAt": "2026-09-10T07:47:47.372600+00:00", "repoId": "BAAI/AREX-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4755598", "taskType": "text-generation"} {"batchId": "9a95cae7b6614130bf9c1de89e7e18e6", "completedAt": "2026-09-10T07:23:17.487528+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-10T07:23:09.465940+00:00", "framework": "vllm-mlu", "intentId": "5253cbeaf413435a975f178c59c5b615", "lastModified": "2026-09-10T05:57:11+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "reason": null, "reconciledAt": "2026-09-10T07:47:47.371518+00:00", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4755805", "taskType": "text-generation"} {"batchId": "67384b00bf014216bfbc730b64c8b024", "completedAt": "2026-09-10T07:33:48.318587+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-10T07:33:41.082504+00:00", "framework": "vllm-patch-tokenizer", "intentId": "aa747b77f05f4b9d89904b945486b169", "lastModified": "2026-09-10T05:57:11+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "reason": null, "reconciledAt": "2026-09-10T07:47:47.371699+00:00", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4756078", "taskType": "text-generation"} -{"batchId": "f561585d65b6436db73c64271aebc791", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-10T07:50:24.500779+00:00", "framework": "vllm", "intentId": "bb32bdded81a4809944edfa8e345c14a", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} +{"batchId": "f561585d65b6436db73c64271aebc791", "completedAt": "2026-09-10T07:50:34.452341+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-10T07:50:24.500779+00:00", "framework": "vllm", "intentId": "bb32bdded81a4809944edfa8e345c14a", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Mthreads_s4000", "taskId": "4756398", "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 12366277..13a7bdac 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 766 + "unified_success_first": 767 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 9, @@ -19,15 +19,15 @@ "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 95, "text-generation|MetaX_c-500|vllm": 87, "text-generation|Mthreads_s4000|llamacpp": 9, - "text-generation|Mthreads_s4000|vllm": 60, + "text-generation|Mthreads_s4000|vllm": 61, "text-generation|Sunrise_pt-200-x1|vllm": 47, "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 50, "text-generation|Vastai_va16|vllm_fix_tokenizer": 35, "text-generation|hygon_k100-ai|llamacpp": 9, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 45 }, - "acceptedSinceRefresh": 766, - "acceptedTotal": 766, - "generatedAt": "2026-09-10T07:33:48.291356+00:00", + "acceptedSinceRefresh": 767, + "acceptedTotal": 767, + "generatedAt": "2026-09-10T07:50:34.415611+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 56cac1d7..60abf30c 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -725,3 +725,4 @@ {"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", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T07:50:25.385741+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4756398", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"} diff --git a/manifest.json b/manifest.json index 0539fd32..55c81b74 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99", ".modelhub_state/recent_outcomes.jsonl": "bfcf9e9826809a4fdb908263410434c0b4285802199616dd05d656397eb47410", ".modelhub_state/recovery_active_tasks.jsonl": "fca2265c9da48ae44f9f4d3e6f9e573c0c7b5ed1c6ca0639d1543be8e3b6733b", - ".modelhub_state/recovery_intents.jsonl": "4bb73df2b8444688efede490fc9f894b4260b7d8cba4fdcf698903a5dc012c1b", - ".modelhub_state/routing_intelligence.json": "eb83338a361c5a8895c58c746b389a6d82f3daaa9b35fed39f08caed18f95baa", + ".modelhub_state/recovery_intents.jsonl": "5168c8f44b2ba1bdac5fb8875ea5cdc2e45da650ad7cb6673356165c61bce829", + ".modelhub_state/routing_intelligence.json": "8a52419d4402861a79d360da797632830eb2c915c1cd189832eea085096de774", ".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03", ".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76", - "ledger/submissions.jsonl": "d85d7d16dc52eb4bc9cd3b20b6a0b0307a1520b6a7cc3da9a8bdeb1103eb84aa", - "outcomes/submissions.jsonl": "563de8ca549dd00c04b7006aa99560ffa514199e0016aa5754207d5266e8c0f9" + "ledger/submissions.jsonl": "9bc9dce5ec67c3c7eabad032da08aef87464e97b729b39da8c6122f5d77e3f17", + "outcomes/submissions.jsonl": "7042c6e7d0bfe22a93357ccba386fd4c266703f2b418fce83a69a2fe04bb2b64" }, - "generation": 5059, - "phase": "intent", + "generation": 5060, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-10T07:50:24.590117+00:00", + "updatedAt": "2026-09-10T07:50:34.622895+00:00", "writerId": "58ff5dc2a2d64b119ad1e4560700f977" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 27eedc32..0782e513 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -595,3 +595,4 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:21:21.949441+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T07:12:26.214438+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755598", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-10T07:23:10.180003+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4755805", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-09-10T07:33:41.787375+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4756078", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "2026-09-10T07:50:25.385741+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4756398", "taskType": "text-generation", "verifyResult": null}