From 0b0e23f546459afb2eae4c5884a1073f68c57080 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 28 Sep 2026 05:24:49 +0000 Subject: [PATCH] state: generation 17747 (result) --- .modelhub_state/recovery_intents.jsonl | 2 +- .modelhub_state/routing_intelligence.json | 10 +++++----- ledger/submissions.jsonl | 1 + manifest.json | 14 +++++++------- outcomes/submissions.jsonl | 1 + 5 files changed, 15 insertions(+), 13 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 4967d46771..811e126860 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2552,7 +2552,7 @@ {"batchId": "7dfff4ac7fb049978110c3e3a01b8030", "completedAt": "2026-09-27T13:45:39.211585+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-27T13:44:58.286855+00:00", "framework": "vllm_fix_tokenizer", "intentId": "00a5545fd4df410a9210b7174cc4cb13", "lastModified": "2026-09-27T13:41:58+00:00", "modelAddress": "https://modelscope.cn/models/Qwen/Qwen3Guard-Stream-0.6B", "reason": null, "reconciledAt": "2026-09-28T05:21:53.471450+00:00", "repoId": "Qwen/Qwen3Guard-Stream-0.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5122549", "taskType": "text-generation"} {"batchId": "7b83ebc5c9594d989c2ea069963747dc", "completedAt": "2026-09-27T14:02:20.694341+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-27T14:01:40.563996+00:00", "framework": "vllm", "intentId": "e1348524182b4ae48cf2076ecdca7558", "lastModified": "2026-09-27T13:41:58+00:00", "modelAddress": "https://modelscope.cn/models/Qwen/Qwen3Guard-Stream-0.6B", "reason": null, "reconciledAt": "2026-09-28T05:21:53.469887+00:00", "repoId": "Qwen/Qwen3Guard-Stream-0.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5122787", "taskType": "text-generation"} {"batchId": "b2f7cab5845f4e098792e34a191f510f", "completedAt": "2026-09-27T18:54:58.563580+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-27T18:53:45.407576+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4c31e6a172174bd2b8ec927a4dd65794", "lastModified": "2026-09-27T18:51:09+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-Flash-Next-OptiQ-2bit", "reason": null, "reconciledAt": "2026-09-28T05:21:53.470627+00:00", "repoId": "mlx-community/Qwen3.8-Flash-Next-OptiQ-2bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5132197", "taskType": "text-generation"} -{"batchId": "ed33bb7bbe04497bb6f1726a835bdf78", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-28T05:24:46.375375+00:00", "framework": "vllm-mlu", "intentId": "1f2bd27e3e474c4ab8ad8aa4e389ca74", "lastModified": "2026-09-24T18:35:22+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-3bit-MLX-TextOnly", "repoId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "ed33bb7bbe04497bb6f1726a835bdf78", "completedAt": "2026-09-28T05:24:49.697594+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-28T05:24:46.375375+00:00", "framework": "vllm-mlu", "intentId": "1f2bd27e3e474c4ab8ad8aa4e389ca74", "lastModified": "2026-09-24T18:35:22+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-3bit-MLX-TextOnly", "reason": null, "repoId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5141843", "taskType": "text-generation"} {"batchId": "179e9ecfe35348deb44f3c5be7efe247", "completedAt": "2026-09-26T04:54:18.911541+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-26T04:54:16.299502+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f015fa059f0d4b85abd1ea1620d3a8cd", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "f9c8240154db42b398dacf34696c5086", "completedAt": "2026-09-24T11:26:48.472659+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-24T11:26:46.008294+00:00", "framework": "vllm_tokenizer_patch", "intentId": "10a1c592a9ee4f11bef9a65c25835867", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "72ad98bd76b64878af3b85496f9b4f2a", "completedAt": "2026-09-24T03:18:53.744906+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-24T03:18:52.675723+00:00", "framework": "vllm-mlu", "intentId": "bc91c43bd85e44bda5e2f46293875f01", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "uniqueness_rejected", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 759f4b953d..7f58223e98 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2691 + "unified_success_first": 2692 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -13,7 +13,7 @@ "text-generation|Biren_166m|vllm_fix_tokenizer": 149, "text-generation|Cambricon_mlu-370-x4|vllm": 73, "text-generation|Cambricon_mlu-370-x4|vllm-customized": 7, - "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 133, + "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 134, "text-generation|Cambricon_mlu-370-x8|vllm": 55, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 71, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 115, @@ -38,8 +38,8 @@ "text-generation|hygon_k100-ai|vllm": 27, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 152 }, - "acceptedSinceRefresh": 2691, - "acceptedTotal": 2691, - "generatedAt": "2026-09-27T18:54:58.468644+00:00", + "acceptedSinceRefresh": 2692, + "acceptedTotal": 2692, + "generatedAt": "2026-09-28T05:24:49.643347+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index b04a03c636..4980994d35 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1039,3 +1039,4 @@ {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-21T18:32:49.780633+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005549", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-09-26T08:01:50.847636+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5097139", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-09-26T08:18:32.495861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5097281", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "submitTime": "2026-09-28T05:24:48.147418+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5141843", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"} diff --git a/manifest.json b/manifest.json index 0e05f331cf..a2e71a7da9 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "e557ed3dc713e441b689ce8cc7bdc2b4e6f41ed1f75f2750fab491d148312d32", ".modelhub_state/recent_outcomes.jsonl": "1dbde9c4996b0dbc395b2b06ede89ee01d228323012054151eb598a3995b826e", ".modelhub_state/recovery_active_tasks.jsonl": "7e5eeb7484b4313aec6afbd25149001183a33904f047ed7fbd8ef5816ff770ac", - ".modelhub_state/recovery_intents.jsonl": "b261e5659dfa53a04419c30bcd52b5b3a6e199dce95f3629c705c045c2be3cc2", - ".modelhub_state/routing_intelligence.json": "783dcdd18e65a6df1db492a367c1d1f213fdc7208da4dc91eec95f41c84a2df2", + ".modelhub_state/recovery_intents.jsonl": "f4bfb6efca1d1fb3067fb2621f79bf92329da237800901cc4d26a435b056e097", + ".modelhub_state/routing_intelligence.json": "3c6264736c5ee3c409f66199313214d8b8062de1f12c8f9cbf2ba72b5d5b1882", ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799", ".modelhub_state/worker_crashes.jsonl": "8f862697b8c8286a6ac8130827f91487a3eb07ecaf4af7ee3de2915d925deb10", - "ledger/submissions.jsonl": "70bfe82770165b8866263fe8d456132117eaf0ab5de0e84d56bd621065a854e1", - "outcomes/submissions.jsonl": "37be82d3448839513a6b9d4379c7c3422fc9268f76f7c0cc972fac2863f13d01" + "ledger/submissions.jsonl": "0ddff7ec5f4bf6c7668ca6c396d209bc8452600c7c14b327abd35750def9f2c9", + "outcomes/submissions.jsonl": "6a9f27a0aeaa31dc9e7259a6d9c0b3f4a6d1531688f0df36659b29e996ca8db5" }, - "generation": 17746, - "phase": "intent", + "generation": 17747, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-28T05:24:46.606822+00:00", + "updatedAt": "2026-09-28T05:24:49.805680+00:00", "writerId": "6e8ddfbd92ca45ccaf79298516f8a6ea" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index e1dd73fc2f..4e9184df92 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -822,3 +822,4 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-27T21:50:00.061732+00:00", "modelId": "Qwen/Qwen3Guard-Stream-0.6B", "modelProfile": {"architectures": ["Qwen3ForGuardModel"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1194258680, "estimatedRequiredGiB": 1.353, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 1210810859, "modelscopeLicense": "apache-2.0", "modelscopeParams": 597111296, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1210817078}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-27T13:45:39.059148+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5122549", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-27T22:03:49.770901+00:00", "modelId": "Qwen/Qwen3Guard-Stream-0.6B", "modelProfile": {"architectures": ["Qwen3ForGuardModel"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1194258680, "estimatedRequiredGiB": 1.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 1210810859, "modelscopeLicense": "apache-2.0", "modelscopeParams": 597111296, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1210817078}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-27T14:02:20.463461+00:00", "targetGpu": "MetaX_c-500", "taskId": "5122787", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-28T03:00:34.545518+00:00", "modelId": "mlx-community/Qwen3.8-Flash-Next-OptiQ-2bit", "modelProfile": {"architectures": ["Qwen4ExpForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 80764996024, "estimatedRequiredGiB": 90.287, "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": 14414328416, "modelscopeTags": ["license:other", "model_type:qwen4_exp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:2bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:ssd-streaming", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 80787002238}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-27T18:53:47.351849+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5132197", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-28T05:24:48.147418+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5141843", "taskType": "text-generation", "verifyResult": null}