From a9549af9c4bafc46f484501ace5701839eec87d5 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 5 Oct 2026 18:17:07 +0000 Subject: [PATCH] state: generation 21023 (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 b1defdd63e..20770ace60 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2700,7 +2700,7 @@ {"batchId": "33341327604d44249b8cdc97dcf3115c", "completedAt": "2026-10-05T06:06:55.149607+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-05T06:05:46.371424+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f9696ee0bba0446688766a14018f381e", "lastModified": "2026-10-05T05:43:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Kolibri-1-NVFP4", "reason": null, "reconciledAt": "2026-10-05T18:07:14.370601+00:00", "repoId": "primitive-ai/Kolibri-1-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5295916", "taskType": "text-generation"} {"batchId": "078f4b1269994d4c8c8a1c0e4b1e06f3", "completedAt": "2026-10-05T16:53:49.606874+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-05T16:52:41.966407+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d6711d02c48a4dafb33869912f5baad0", "lastModified": "2026-09-08T05:28:50+00:00", "modelAddress": "https://modelscope.cn/models/rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "reason": null, "reconciledAt": "2026-10-05T18:07:14.370455+00:00", "repoId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5305971", "taskType": "text-generation"} {"batchId": "66398e18f2aa4aa6b83675255b3eb0a0", "completedAt": "2026-10-05T17:11:20.398975+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-05T17:11:19.012773+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f2f7a0fec18c41f2a579e6f135dfdbef", "lastModified": "2026-09-08T05:28:50+00:00", "modelAddress": "https://modelscope.cn/models/rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "reason": null, "reconciledAt": "2026-10-05T18:07:14.370956+00:00", "repoId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5306227", "taskType": "text-generation"} -{"batchId": "4eeadeb2b3a44f28a5dc31a0b805414f", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-05T18:15:37.875183+00:00", "framework": "vllm_tokenizer_patch", "intentId": "970c221c6be2404d86b3654544d26173", "lastModified": "2026-10-05T18:02:26+00:00", "modelAddress": "https://modelscope.cn/models/unsloth/gpt-oss-20b-bnb-4bit", "repoId": "unsloth/gpt-oss-20b-bnb-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "4eeadeb2b3a44f28a5dc31a0b805414f", "completedAt": "2026-10-05T18:17:07.212061+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-05T18:15:37.875183+00:00", "framework": "vllm_tokenizer_patch", "intentId": "970c221c6be2404d86b3654544d26173", "lastModified": "2026-10-05T18:02:26+00:00", "modelAddress": "https://modelscope.cn/models/unsloth/gpt-oss-20b-bnb-4bit", "reason": null, "repoId": "unsloth/gpt-oss-20b-bnb-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "5307270", "taskType": "text-generation"} {"batchId": "9544bf0548e54a8e93c3adfd9bffb52a", "completedAt": "2026-10-03T16:15:51.005765+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-10-03T16:13:49.532883+00:00", "framework": "vllm-patch-tokenizer", "intentId": "7f7cb1b51f944ac58018ee2e42ca61f7", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} {"batchId": "6ad67bedd5104b958247ed686fa4a8d7", "completedAt": "2026-09-29T14:16:48.925444+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T14:16:45.683768+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ba30792e89b44ef5804d5f3613d7df71", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} {"batchId": "6ad67bedd5104b958247ed686fa4a8d7", "completedAt": "2026-09-29T14:16:48.925408+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T14:16:45.683638+00:00", "framework": "vllm_tokenizer_patch", "intentId": "69aec4d25f21464c860135eb90d77735", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index ab1251edef..d4e43c3f08 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,11 +1,11 @@ { "acceptedByCategory": { - "unified_success_first": 2839 + "unified_success_first": 2840 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 26, "text-generation|Ascend_910-b3|vllm": 40, - "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 229, + "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 230, "text-generation|Ascend_910-b4|llamacpp": 18, "text-generation|Ascend_910-b4|vllm": 33, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 216, @@ -39,8 +39,8 @@ "text-generation|hygon_k100-ai|vllm": 27, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 153 }, - "acceptedSinceRefresh": 2839, - "acceptedTotal": 2839, - "generatedAt": "2026-10-05T17:11:20.355812+00:00", + "acceptedSinceRefresh": 2840, + "acceptedTotal": 2840, + "generatedAt": "2026-10-05T18:17:07.170452+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index c6a366e524..adf4417817 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -947,3 +947,4 @@ {"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_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/unsloth/gpt-oss-20b-bnb-4bit", "modelId": "unsloth/gpt-oss-20b-bnb-4bit", "submitTime": "2026-10-05T18:17:07.068675+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5307270", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} diff --git a/manifest.json b/manifest.json index d4951e4d0f..b0efd0176d 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "62164f6cc93d220ca55c1a0e4a07f48ad5dc298f03e4e8cb41cb3f06d29eabde", ".modelhub_state/recent_outcomes.jsonl": "66f65405defcf850f044e43e54c3dc291f18521f309cb9962d861b493cb049ac", ".modelhub_state/recovery_active_tasks.jsonl": "e00f4782d96ff9fb1c16b0da16ec32081a76303deb827320dd5240e490d7e114", - ".modelhub_state/recovery_intents.jsonl": "f78c54fc1776bc57638cb75d7b1815ca6f517b16911e974efe2bff8e0a166211", - ".modelhub_state/routing_intelligence.json": "77d8b4dce487f558f2bfad70070ec90562040089a37f294cc61c343c5fe6e1f9", + ".modelhub_state/recovery_intents.jsonl": "b3da2f5add75360234176996975b5566ccf756cf98a28c586f84865ff6b3fb5c", + ".modelhub_state/routing_intelligence.json": "0d199cc8f75a82a00458709b87f8ca103baa6d2ff32af85ea09e3fc50e71b3a7", ".modelhub_state/submission_exclusions.jsonl": "8a533753b09639322718ffe59fad6a6f11e8cc3741d7be12085a149c97ca5507", ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f", - "ledger/submissions.jsonl": "047a74273cf4a9b9c0546d544300b29dcabd1458f587b06af2308c8c6fa9b4f5", - "outcomes/submissions.jsonl": "2a90128a2fd4277903e0bce61cd9ea419726916bb58a4b81b2bcb4014ac09c6f" + "ledger/submissions.jsonl": "c6629cbc22c28d3e5d8488909d3db064016ddf95a412c167265539f0e8b3c440", + "outcomes/submissions.jsonl": "894ce672862471b554036ebd9065a84510af9f1316eb7e58d372a43b4a0f9d2f" }, - "generation": 21022, - "phase": "intent", + "generation": 21023, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-10-05T18:15:37.994663+00:00", + "updatedAt": "2026-10-05T18:17:07.371756+00:00", "writerId": "c99196ebc91b43dbbcacb4830cce7e56" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 77317bebd8..07e80e76fc 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -724,3 +724,4 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-05T14:15:08.848422+00:00", "modelId": "primitive-ai/Kolibri-1-NVFP4", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47707345296, "estimatedRequiredGiB": 53.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 42896496000, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 47737939154, "repositoryOnDiskBytes": 47737939154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-05T06:06:54.870782+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5295916", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474195, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320426072, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:fp16", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 16320426072, "quantizationMethod": null, "recursiveRepositoryBytes": 16320426072, "repositoryOnDiskBytes": 16320426072}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-05T16:53:48.247093+00:00", "targetGpu": "MetaX_c-500", "taskId": "5305971", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474195, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320426072, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:fp16", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 16320426072, "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "recursiveRepositoryBytes": 16320426072, "repositoryOnDiskBytes": 16320426072}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-05T17:11:20.150043+00:00", "targetGpu": "Biren_166m", "taskId": "5306227", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "unsloth/gpt-oss-20b-bnb-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 40884615394, "estimatedRequiredGiB": 45.723, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 40912596558, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20934761652, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:openai", "custom_tag:unsloth"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 40912596558, "quantizationMethod": "bitsandbytes", "recursiveRepositoryBytes": 40912599808, "repositoryOnDiskBytes": 40912599808}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-05T18:17:07.068675+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5307270", "taskType": "text-generation", "verifyResult": null}