From 197b17298b3b29919320cd1e0e48596c763ffe0e Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Sun, 20 Sep 2026 09:09:39 +0000 Subject: [PATCH] state: generation 10417 (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 daeeaa4e37..64c434fad5 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1595,7 +1595,7 @@ {"batchId": "32beace4dd824c5f99caf15f71cacef7", "completedAt": "2026-09-20T09:07:26.792809+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:00:59.213967+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d86806817adc462fbf56610dfbce6ebc", "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": "2026-09-20T09:09:04.885630+00:00", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "4974424", "taskType": "text-generation"} {"batchId": "32beace4dd824c5f99caf15f71cacef7", "completedAt": "2026-09-20T09:07:26.792812+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:00:59.214011+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6800271ece9d4b2685084eef33b529df", "lastModified": "2026-09-01T03:45:04+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "reason": null, "reconciledAt": "2026-09-20T09:09:04.884395+00:00", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "4974425", "taskType": "text-generation"} {"batchId": "32beace4dd824c5f99caf15f71cacef7", "completedAt": "2026-09-20T09:07:26.792830+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:00:59.214339+00:00", "framework": "transformers", "intentId": "67d0c946aa33456897b905774ea87097", "lastModified": "2026-08-26T18:34:54+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "reason": null, "reconciledAt": "2026-09-20T09:09:04.887424+00:00", "repoId": "ornith-ai/Ornith-1.5-9B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "4974501", "taskType": "text-generation"} -{"batchId": "4167375da4e14cd28313058231752f71", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:09:31.628872+00:00", "framework": "vllm", "intentId": "91414bd72b2f45d8ad775546fe4d8013", "lastModified": "2026-09-19T14:40:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} +{"batchId": "4167375da4e14cd28313058231752f71", "completedAt": "2026-09-20T09:09:39.770893+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:09:31.628872+00:00", "framework": "vllm", "intentId": "91414bd72b2f45d8ad775546fe4d8013", "lastModified": "2026-09-19T14:40:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4974664", "taskType": "text-generation"} {"batchId": "b37382fdd745426db7b1ad8215597fa9", "completedAt": "2026-09-20T09:09:02.433172+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:07:27.652424+00:00", "framework": "vllm", "intentId": "fd895c19603a4722bbcc3c61b7f9b80c", "repoId": "bharatgenai/Param2-17B-A2.4B-Thinking", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} {"batchId": "b37382fdd745426db7b1ad8215597fa9", "completedAt": "2026-09-20T09:09:02.433169+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:07:27.652365+00:00", "framework": "vllm-customized", "intentId": "7de37ff44c8c44c2b22cae69a63eed68", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} {"batchId": "b37382fdd745426db7b1ad8215597fa9", "completedAt": "2026-09-20T09:09:02.433166+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T09:07:27.652306+00:00", "framework": "vllm-customized", "intentId": "b54e168b3db34ec49330de7a2f5256d2", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "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 44481a4885..64a8a85dba 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 1735 + "unified_success_first": 1736 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -14,7 +14,7 @@ "text-generation|Cambricon_mlu-370-x4|vllm": 48, "text-generation|Cambricon_mlu-370-x4|vllm-customized": 2, "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 80, - "text-generation|Cambricon_mlu-370-x8|vllm": 50, + "text-generation|Cambricon_mlu-370-x8|vllm": 51, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 26, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 90, "text-generation|Iluvatar_bi-150|llamacpp": 16, @@ -37,8 +37,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 107 }, - "acceptedSinceRefresh": 1735, - "acceptedTotal": 1735, - "generatedAt": "2026-09-20T09:09:02.371265+00:00", + "acceptedSinceRefresh": 1736, + "acceptedTotal": 1736, + "generatedAt": "2026-09-20T09:09:39.714331+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index b95f235b85..9748548ac8 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1067,3 +1067,4 @@ {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "submitTime": "2026-09-20T08:53:34.985766+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974282", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "submitTime": "2026-09-20T08:53:35.105220+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974283", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-20T08:54:12.459339+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974306", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "submitTime": "2026-09-20T09:09:39.664442+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4974664", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index 707c6c97ab..000160ba75 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "d5763a40bf9f7d802c551a5c47a0842c547d3e07c05c0ad2f9da1970ee45cc83", ".modelhub_state/recent_outcomes.jsonl": "e4ec7fe7a933ada1495dda90138340a94157c38bdea2cbc2d2155d9b305ba72e", ".modelhub_state/recovery_active_tasks.jsonl": "e3f09807dd2ae8549a843d9bbca706361e4e8968f4b3357c94fca6b7cf0ebfdf", - ".modelhub_state/recovery_intents.jsonl": "621f1d9aa6de786b5bc69518e265fade25313493c174946bef5e3e67d9ccdbbe", - ".modelhub_state/routing_intelligence.json": "5bb7f2842e4d1dc41aced6ce58d3258bc6d63f8471d7ef4296d9b6de68ed23b3", + ".modelhub_state/recovery_intents.jsonl": "ba2bae86d4c90d3f408905a894ff9c650bc53fb01f72ced2f5cc086a8ae808f8", + ".modelhub_state/routing_intelligence.json": "a4d25f10aae55c18937d9fe3b36a0cca075eeced7472765233de8cd528d9fdbb", ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "2bf42465d33c349e0a0ccc8a8d4b1a84c3d7aa43f6cd4c345e5415e32fb27168", - "outcomes/submissions.jsonl": "99d0042471cbc88a23c547b728ed6ae42aa2e99771d89ce9aed6dc216e31e895" + "ledger/submissions.jsonl": "5fc5650c07784d535466aff30a244b0e2c5f1bb19e91e76e5b25a748d47e2923", + "outcomes/submissions.jsonl": "a267c77556bad741c4229f76492894c63b25055d40ae537698771222e7d8b1ce" }, - "generation": 10416, - "phase": "intent", + "generation": 10417, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-20T09:09:31.758007+00:00", + "updatedAt": "2026-09-20T09:09:39.871928+00:00", "writerId": "fc715c06e24c4db2ae3e425e435db996" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 243f39dbff..d400b0e3e1 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1108,3 +1108,4 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": 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": "2026-09-20T09:03:34.821144+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974424", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22210552448, "estimatedRequiredGiB": 24.849, "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": 22234091413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 17463440388, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "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:speculative-decoding", "custom_tag:blackwell", "custom_tag:a100"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 22234091413}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T09:03:34.948874+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974425", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "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": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T09:04:12.649418+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974501", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T09:09:39.664442+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4974664", "taskType": "text-generation", "verifyResult": null}