diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 246b01a1f..8bd777613 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3239,7 +3239,7 @@ {"batchId": "9051f07a8dcd4bc3a217cfcc3f596181", "completedAt": "2026-10-07T20:33:04.415550+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T20:31:40.597548+00:00", "framework": "vllm_fix_tokenizer", "intentId": "425c318457ea4288a1698a30e4787ee0", "lastModified": "2026-09-15T15:06:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-9B-OptiQ-4bit", "reason": null, "reconciledAt": "2026-10-08T03:30:43.642951+00:00", "repoId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5361261", "taskType": "text-generation"} {"batchId": "db73439bbd07499cb98b7842d424608b", "completedAt": "2026-10-07T21:43:55.329566+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-10-07T21:42:15.517760+00:00", "framework": "vllm", "intentId": "27173d26a8cf4a749bea9ec1dcf092d6", "lastModified": "2026-10-07T17:37:13+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "reason": null, "reconciledAt": "2026-10-08T03:30:43.639984+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5362155", "taskType": "text-generation"} {"batchId": "f2bc60a09f214be6942517a4e455ed82", "completedAt": "2026-10-07T22:51:48.821998+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-10-07T22:49:55.689819+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "7a5c5e77cb244e6abedde1e588aaaa1f", "lastModified": "2026-10-07T17:37:13+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "reason": null, "reconciledAt": "2026-10-08T03:30:43.640264+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5363028", "taskType": "text-generation"} -{"batchId": "527cd8d84a824073b7716e2ad678ff02", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-08T03:54:59.044369+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6a847c379f60490f834458640a3261d3", "lastModified": "2026-08-31T16:06:01+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "repoId": "XHToken/Spark-X2.5-1.7B-Base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} +{"batchId": "527cd8d84a824073b7716e2ad678ff02", "completedAt": "2026-10-08T03:56:51.825606+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-08T03:54:59.044369+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6a847c379f60490f834458640a3261d3", "lastModified": "2026-08-31T16:06:01+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "reason": null, "repoId": "XHToken/Spark-X2.5-1.7B-Base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "MetaX_c-500", "taskId": "5367428", "taskType": "text-generation"} {"batchId": "6aa7248a7b3546dba73bdb92d9a77079", "completedAt": "2026-10-07T20:18:36.848910+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T19:40:31.784067+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2f0cb6ccdecc4316b55609675cbdd668", "repoId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "6aa7248a7b3546dba73bdb92d9a77079", "completedAt": "2026-10-07T20:18:36.848903+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T19:40:31.783981+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e743bd075d9a4fef818c147bbe312063", "repoId": "ibm-granite/granite-4.2-30b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "6aa7248a7b3546dba73bdb92d9a77079", "completedAt": "2026-10-07T20:18:36.848900+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T19:40:31.783937+00:00", "framework": "vllm_fix_tokenizer", "intentId": "55a1a393950e454a964334b9ea2f0089", "repoId": "danish-foundation-models/DFM-Mimir-v1.5", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 212b27817..b2125cc5f 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 3378 + "unified_success_first": 3379 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 29, @@ -29,7 +29,7 @@ "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 298, "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 98, "text-generation|MetaX_c-500|vllm": 128, - "text-generation|MetaX_c-500|vllm_tokenizer_patch": 85, + "text-generation|MetaX_c-500|vllm_tokenizer_patch": 86, "text-generation|Mthreads_s4000|llamacpp": 27, "text-generation|Mthreads_s4000|vllm": 175, "text-generation|Sunrise_pt-200-x1|vllm": 87, @@ -39,8 +39,8 @@ "text-generation|hygon_k100-ai|vllm": 32, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 218 }, - "acceptedSinceRefresh": 3378, - "acceptedTotal": 3378, - "generatedAt": "2026-10-07T22:51:48.749046+00:00", + "acceptedSinceRefresh": 3379, + "acceptedTotal": 3379, + "generatedAt": "2026-10-08T03:56:51.762343+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index f596a9901..b41cad96e 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1040,3 +1040,4 @@ {"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "submitTime": "2026-10-07T19:30:29.945877+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360309", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"} {"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "submitTime": "2026-10-07T19:30:30.071008+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360316", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"} {"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "submitTime": "2026-10-07T19:30:30.057671+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360317", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T03:55:00.884003+00:00", "targetGpu": "MetaX_c-500", "taskId": "5367428", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} diff --git a/manifest.json b/manifest.json index 4894fe2ff..a0644ab8e 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "290fd20f2a44f9b6d57eef1cdb419706d3c80669a13e64e254b073aeb5dcf890", ".modelhub_state/recent_outcomes.jsonl": "4ef7ee44fec878b981e70399bf9f8a40f933af061c0cc3f40227735e43f4c795", ".modelhub_state/recovery_active_tasks.jsonl": "c9e6c68b9630120a9e186cf2bc454fa7611a4683df2c1e61e79d6f15a52035b3", - ".modelhub_state/recovery_intents.jsonl": "0e08f1e480611a482fe575d88490c88fa9056aaeaeff1e4c14e6d4d7289d3652", - ".modelhub_state/routing_intelligence.json": "a312187abffa011156b64da1fed551d1816329b725ab3f38c5221900b7cc793e", + ".modelhub_state/recovery_intents.jsonl": "87550d59eb011ca3b2fca0c99588e1dc153161350cb7da7e3373efe07587f3ce", + ".modelhub_state/routing_intelligence.json": "a1c98727f3c8cb7b27de1e590c6160623baf7fd4f38529510e352ae3b00c73b3", ".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b", ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f", - "ledger/submissions.jsonl": "52621bd2c4995762cf48c9be99e451bbf591cf6e36166b89627f588fe7599163", - "outcomes/submissions.jsonl": "fccc9928461a7fe64bb5544e70074b7b2655632d325e585ee43c70f848bcf4ed" + "ledger/submissions.jsonl": "1fb4258830058ce70f340d4c34dde71df50185b0a64b9771185fb58824777fd8", + "outcomes/submissions.jsonl": "1de9f8137f075fd787edcd9acd7dd2f003c0e9bd1d46669060e5e7848b063b58" }, - "generation": 22042, - "phase": "intent", + "generation": 22043, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-10-08T03:54:59.270716+00:00", + "updatedAt": "2026-10-08T03:56:51.954467+00:00", "writerId": "33ed03361c5848e88b8ce6204fb4f7d2" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index a26a8e0d0..fb3387135 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -964,3 +964,4 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "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": 7120900461, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1915564544, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:qwen3.5", "custom_tag:reasoning", "custom_tag:long-context", "custom_tag:function-calling", "custom_tag:tool-use", "custom_tag:agentic", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-07T14:46:46.372736+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": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 7120900461}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T20:33:02.759018+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361261", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580753, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580753}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T21:42:18.062092+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5362155", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580753, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580753}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T22:49:57.464476+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5363028", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "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": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-08T03:55:00.884003+00:00", "targetGpu": "MetaX_c-500", "taskId": "5367428", "taskType": "text-generation", "verifyResult": null}