From 3dc406db0630f2113870eeb3684f151fd918554a Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Sun, 20 Sep 2026 14:48:06 +0000 Subject: [PATCH] state: generation 10636 (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 0e0c65cfd..53e9b5f82 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1682,7 +1682,7 @@ {"batchId": "c208b2f645614a14a05f569686eaa8f0", "completedAt": "2026-09-20T14:43:55.731125+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:37:40.025509+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cbea23846c1041d390683bf19aa2e1e3", "lastModified": "2026-08-24T19:06:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-20T14:46:28.823206+00:00", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4980558", "taskType": "text-generation"} {"batchId": "c208b2f645614a14a05f569686eaa8f0", "completedAt": "2026-09-20T14:43:55.731149+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:37:40.025941+00:00", "framework": "vllm_tokenizer_patch", "intentId": "945ed355fc854c3796bff67a188dc1a4", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-20T14:46:28.824536+00:00", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4980575", "taskType": "text-generation"} {"batchId": "c208b2f645614a14a05f569686eaa8f0", "completedAt": "2026-09-20T14:43:55.731183+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:37:40.026474+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cc61d16ed90546aa8cdaefcc5b85acf3", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-20T14:46:28.824533+00:00", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4980576", "taskType": "text-generation"} -{"batchId": "feb78ef0c18e4e3985359b64b1296b80", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:48:03.991748+00:00", "framework": "vllm-customized", "intentId": "71511ea3fb1c4043b4770c7db4bb7a60", "lastModified": "2026-09-14T13:40:21+00:00", "modelAddress": "https://modelscope.cn/models/IntervitensInc/kek_mk3", "repoId": "IntervitensInc/kek_mk3", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} +{"batchId": "feb78ef0c18e4e3985359b64b1296b80", "completedAt": "2026-09-20T14:48:06.593877+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:48:03.991748+00:00", "framework": "vllm-customized", "intentId": "71511ea3fb1c4043b4770c7db4bb7a60", "lastModified": "2026-09-14T13:40:21+00:00", "modelAddress": "https://modelscope.cn/models/IntervitensInc/kek_mk3", "reason": null, "repoId": "IntervitensInc/kek_mk3", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4980632", "taskType": "text-generation"} {"batchId": "25ba0a4da7e34622a6702513d8cdc4ce", "completedAt": "2026-09-20T14:46:26.841216+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:43:59.030327+00:00", "framework": "vllm", "intentId": "6552e2f86a624809a049273684b0db69", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "25ba0a4da7e34622a6702513d8cdc4ce", "completedAt": "2026-09-20T14:46:26.841213+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:43:59.030267+00:00", "framework": "vllm", "intentId": "d4a6ec4d041443a3aa7cbe85d6570cfb", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "25ba0a4da7e34622a6702513d8cdc4ce", "completedAt": "2026-09-20T14:46:26.841210+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:43:59.030208+00:00", "framework": "vllm", "intentId": "c4efb924449747e090a8b2f171754135", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index bc030210a..14975018b 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 1822 + "unified_success_first": 1823 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -15,7 +15,7 @@ "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": 55, - "text-generation|Cambricon_mlu-370-x8|vllm-customized": 31, + "text-generation|Cambricon_mlu-370-x8|vllm-customized": 32, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 91, "text-generation|Iluvatar_bi-150|llamacpp": 16, "text-generation|Iluvatar_bi-150|transformers": 30, @@ -37,8 +37,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 109 }, - "acceptedSinceRefresh": 1822, - "acceptedTotal": 1822, - "generatedAt": "2026-09-20T14:46:26.777607+00:00", + "acceptedSinceRefresh": 1823, + "acceptedTotal": 1823, + "generatedAt": "2026-09-20T14:48:06.524036+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index c42a816cc..be3627092 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1105,3 +1105,4 @@ {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-20T11:44:01.235722+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4978143", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-20T12:41:32.800701+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979069", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "modelId": "aisingapore/SEA-LION-v1-7B", "submitTime": "2026-09-20T12:55:19.835166+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979183", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"} +{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/IntervitensInc/kek_mk3", "modelId": "IntervitensInc/kek_mk3", "submitTime": "2026-09-20T14:48:06.475114+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4980632", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index 5b3474c91..eeb9d44b8 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "eb01f106d0cd4018a0346c4a81182d6a9e67f5d4d14db22f5d0c685667977bc3", ".modelhub_state/recent_outcomes.jsonl": "c686c563ab48519884fd42d9952589ca0656ee5a5fab0f1556f4f5dc80e978ff", ".modelhub_state/recovery_active_tasks.jsonl": "9e0d5d0e0ca2e6fe45bf814462091e89c6625c7005e5953f84cfe1ed47a7d8fc", - ".modelhub_state/recovery_intents.jsonl": "aafa001d637156e6d3e306648d301fc077a04c4aa74f131f6a7dc9d258671531", - ".modelhub_state/routing_intelligence.json": "87ca00c8bdf8c0f050aa5b51768054f887caeeb2cc3d9144da6a05b86ddde4e3", + ".modelhub_state/recovery_intents.jsonl": "f07e58b95ef9c9ad7a72e6f1b28afa571451315d2665f4ae76de7b87ce4dd7a9", + ".modelhub_state/routing_intelligence.json": "76d5a555f3a78f8d4ff9b627b9dfe1bd2920e69f743d08781d7c84d2921b9fba", ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "f5217e09fdbe3d527514101f8ffc3469765469f1e06305c1a32a40055965d60c", - "outcomes/submissions.jsonl": "9dd091c37ef249704e36df327ea233cc74c00589fc1e72b8a5e8e170e8af36c8" + "ledger/submissions.jsonl": "381e2b6a42770de4e0a03607ea8f6c62649d4eb556d28209549a9833e1999106", + "outcomes/submissions.jsonl": "6de96e2e866a87cbb5617d2aa173fb5d598b78c4a322722850dd9d4db40419d6" }, - "generation": 10635, - "phase": "intent", + "generation": 10636, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-20T14:48:04.134747+00:00", + "updatedAt": "2026-09-20T14:48:06.755713+00:00", "writerId": "fc715c06e24c4db2ae3e425e435db996" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index f36f19034..b5533c1a6 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1098,3 +1098,4 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385522016, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407346443, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407346443}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:37:47.736818+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980558", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457730, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096457730}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:38:07.337494+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4980575", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020564058, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020564058}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:39:32.708014+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980576", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "IntervitensInc/kek_mk3", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3289069288, "estimatedRequiredGiB": 3.683, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 3295875324, "modelscopeLicense": null, "modelscopeParams": 1644515328, "modelscopeTags": ["model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3295875324}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:48:06.475114+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4980632", "taskType": "text-generation", "verifyResult": null}