From bed6d0a30e3726347716957b2a1de4c4b3c900b7 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 26 Oct 2026 05:06:13 +0000 Subject: [PATCH] state: generation 37914 (intent) --- .../architecture_compatibility_blacklist.json | 2 +- .modelhub_state/market_intelligence.json | 2 +- .modelhub_state/official_capabilities.json | 36 ++++++++++--------- .modelhub_state/recovery_intents.jsonl | 12 +++++++ manifest.json | 16 ++++----- outcomes/submissions.jsonl | 14 ++++---- 6 files changed, 48 insertions(+), 34 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 62812ec486..f031ba9c27 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -567,7 +567,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-26T05:04:35.350833+00:00", + "generatedAt": "2026-10-26T05:06:12.423859+00:00", "summary": { "activeBlockCount": 28, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index f39f4d4f3b..3bf71f2e0c 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-26T05:04:35.483813+00:00", + "generatedAt": "2026-10-26T05:06:12.572286+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 5ca69820cc..43b4915885 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-26T05:04:35.483813+00:00", + "catalogUpdatedAt": "2026-10-26T05:06:12.572286+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-26T05:04:35.717296+00:00", + "generatedAt": "2026-10-26T05:06:12.788936+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -497,6 +497,14 @@ ], "updatedAt": "2026-10-26T04:56:15.246458+00:00" }, + "https://modelscope.cn/models/IFM/Jais-3-32B-FP8|2026-10-25T15:26:39+00:00|Ascend_910-b4": { + "taskTypes": [ + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-10-26T05:06:12.788936+00:00" + }, "https://modelscope.cn/models/IFM/Jais-3-32B-FP8|2026-10-25T15:26:39+00:00|Biren_166m": { "taskTypes": [ "text-generation" @@ -1705,14 +1713,6 @@ ], "updatedAt": "2026-10-26T04:56:16.788725+00:00" }, - "https://modelscope.cn/models/agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF|2026-10-25T15:18:29+00:00|Ascend_910-b4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-10-26T04:37:17.774236+00:00" - }, "https://modelscope.cn/models/agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF|2026-10-25T15:18:29+00:00|Biren_166m": { "taskTypes": [ "text-generation" @@ -1736,12 +1736,6 @@ ], "updatedAt": "2026-10-26T04:45:33.218602+00:00" }, - "https://modelscope.cn/models/agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF|2026-10-25T15:18:29+00:00|Kunlunxin_p-800": { - "taskTypes": [ - "text-generation" - ], - "updatedAt": "2026-10-26T04:37:17.722473+00:00" - }, "https://modelscope.cn/models/agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF|2026-10-25T15:18:29+00:00|Mthreads_s4000": { "taskTypes": [ "text-generation", @@ -4935,6 +4929,14 @@ ], "updatedAt": "2026-10-26T04:56:17.667122+00:00" }, + "https://modelscope.cn/models/siliconflow/DeepSeek-V4.1-Flash-SF-WFP4AFP8|2026-10-26T03:02:59+00:00|Ascend_910-b4": { + "taskTypes": [ + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-10-26T05:06:12.774166+00:00" + }, "https://modelscope.cn/models/siliconflow/DeepSeek-V4.1-Flash-SF-WFP4AFP8|2026-10-26T03:02:59+00:00|Biren_166m": { "taskTypes": [ "text-generation" @@ -6158,6 +6160,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-26T05:04:35.483813+00:00", + "taskTreeUpdatedAt": "2026-10-26T05:06:12.572286+00:00", "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index a26e8eb2b6..9890c65950 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3910,6 +3910,18 @@ {"batchId": "fe98bbe446c14af8a16cdb62a7b98b31", "completedAt": "2026-10-26T04:18:05.784406+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:18:03.639774+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c247cd656eae4a09b91a60ea09c880db", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-26T05:04:40.900121+00:00", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5795832", "taskType": "text-generation"} {"batchId": "fe98bbe446c14af8a16cdb62a7b98b31", "completedAt": "2026-10-26T04:18:05.784423+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:18:03.639988+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b3037b062d56438fae3946cac4f3ff6c", "lastModified": "2026-10-21T18:55:40+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-bf16", "reason": null, "reconciledAt": "2026-10-26T05:04:40.899706+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5795834", "taskType": "text-generation"} {"batchId": "c6c7b47e653540aa9ff30c6db5212b63", "completedAt": "2026-10-26T04:19:03.775975+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:19:01.480725+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cc0e62c204e742fa9a40633ce402167c", "lastModified": "2026-10-21T15:51:34+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/granite-4.0-h-tiny-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-26T05:04:40.901508+00:00", "repoId": "cyankiwi/granite-4.0-h-tiny-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5795848", "taskType": "text-generation"} +{"batchId": "0e75096038d24eb19a828900bcca75bf", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:06:13.294919+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b480731bfd5e4940b4fa1156d8e297b7", "lastModified": "2026-10-25T13:17:58+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-5bit-MLX", "repoId": "ukisai/Swift-1.5-5bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "0e75096038d24eb19a828900bcca75bf", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:06:13.295023+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1aeb42ed78894158b4f2a986d0f8605f", "lastModified": "2026-10-21T16:21:36+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "0e75096038d24eb19a828900bcca75bf", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:06:13.295071+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8ddae920dfbf4459885f19b51f69da39", "lastModified": "2026-10-21T17:04:56+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "repoId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "0e75096038d24eb19a828900bcca75bf", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:06:13.295116+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f188db76363247d193614c29a65450f1", "lastModified": "2026-10-25T13:57:34+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "repoId": "cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "0e75096038d24eb19a828900bcca75bf", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:06:13.295160+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9c9111bde54c464eb8451fedf4c05702", "lastModified": "2026-10-21T16:38:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "0e75096038d24eb19a828900bcca75bf", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:06:13.295211+00:00", "framework": "vllm_fix_tokenizer", "intentId": "27bd68ece81242438691d2c7620c5739", "lastModified": "2026-10-21T16:49:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "0e75096038d24eb19a828900bcca75bf", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:06:13.295256+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ddd32f1be86440a089cefa1b17a7c86f", "lastModified": "2026-10-21T17:02:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "0e75096038d24eb19a828900bcca75bf", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:06:13.295300+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bc1e6cdfca8b4e008ff54d66c67cd562", "lastModified": "2026-10-21T16:31:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "0e75096038d24eb19a828900bcca75bf", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:06:13.295343+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e4db5c53c7ef4bab8cf1ddf22f56b174", "lastModified": "2026-10-21T17:00:21+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/LFM2-8B-A1B-AWQ-4bit", "repoId": "cyankiwi/LFM2-8B-A1B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "0e75096038d24eb19a828900bcca75bf", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:06:13.295387+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8234d551ec014b678decf564e5f9afd5", "lastModified": "2026-10-21T16:58:14+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-4bit", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "0e75096038d24eb19a828900bcca75bf", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:06:13.295430+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1dd2c89dce334e9e9f6e00cd48135c01", "lastModified": "2026-10-21T17:09:55+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "0e75096038d24eb19a828900bcca75bf", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:06:13.295474+00:00", "framework": "vllm_fix_tokenizer", "intentId": "97f44c66065f415b9ae90a947363ad9d", "lastModified": "2026-10-21T16:41:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} {"batchId": "e8d1af42c72e4ba687e519d6aa42b92c", "completedAt": "2026-10-26T05:04:38.832883+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:04:36.292711+00:00", "framework": "vllm_fix_tokenizer", "intentId": "74e24f256e8047dcb178d1f3b1ad8d8b", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "e8d1af42c72e4ba687e519d6aa42b92c", "completedAt": "2026-10-26T05:04:38.832879+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:04:36.292668+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fdaab4b85c474b7ab8403a003ca9e1d0", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "e8d1af42c72e4ba687e519d6aa42b92c", "completedAt": "2026-10-26T05:04:38.832876+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:04:36.292624+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ffcd88672a6741d0b96f577afd45bb74", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index a99678abaf..b8afa3642d 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "ce19769dc86475dcc673b7a86d414fd52b70f271d6a1f7720169dfad4f39045a", - ".modelhub_state/architecture_compatibility_blacklist.json": "06fbd017e5d6586e8ffeb51a9d8cc3d8fb5479ba9c419b286041918527088f8c", + ".modelhub_state/architecture_compatibility_blacklist.json": "65ac6251eb62dbe93ddcf66f2d9e888e3a018d3475b58518a268a38e0e46e882", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "80b7b1e15808d4bd9ed1f2d4e560a9d952728a4d8892ea58e1cc4c8a6a013676", - ".modelhub_state/official_capabilities.json": "277a183d1aa44bca993b3701db4fa07e2b7704372ed3212eb8141e8f46ceec00", + ".modelhub_state/market_intelligence.json": "205eabdf2a084b135bd8363ca3b75769531afc6d14ff5bccd2781b35ffc7b70b", + ".modelhub_state/official_capabilities.json": "f3631022d07ef6b7653b4e92093e71d76e86c569feffa862bbf98b7bd811aca8", ".modelhub_state/outcome_checkpoint.json": "31a52aa7925b56683e751617c1fa4c55a415b1c12c3a92e510cee04e55cdef39", ".modelhub_state/queue_cleanup_latest.json": "7bb32e50f3732b4804980b5ffecedb37f0ecab728fd25cde56ed3db8bd88bb98", ".modelhub_state/recent_outcomes.jsonl": "bb6f4ee6ba6da47a0697c3cf5fb9019c4d60b699f04694e45972407d89bd0363", ".modelhub_state/recovery_active_tasks.jsonl": "4ac7fe44ef0aaac9bb67f971c65da4f6c6f5a42e71092845d7c609ecdf101356", - ".modelhub_state/recovery_intents.jsonl": "6024fa6e1f5b427bd04d90f3b46e711b7b9c5c79bab1a6cbc2c0467c2e5dfdc9", + ".modelhub_state/recovery_intents.jsonl": "fc00231905a85e67398167dfe9f94d283a23e0ae5b8a0b7bfa03f97473cfb784", ".modelhub_state/routing_intelligence.json": "655d0a95aa18ff45b102d7aabf07c4294937a5c6b4e498c1687e4a6cb6997be0", ".modelhub_state/submission_exclusions.jsonl": "bec721d27d733285faddfa9c457d1882988a145ee87f4fbf285ac5deb38326c9", ".modelhub_state/worker_crashes.jsonl": "2a418db914481d815151923dc46f4e4ad1154d9195fad06fee6275702f33c0b9", "ledger/submissions.jsonl": "4499d1e0f10f75b2308c7fb4824c2fb1fe7ed81b29d97adf7b0d49bda29e1786", - "outcomes/submissions.jsonl": "b0eae3df24956f701d65de492c09e16430d1258ffbebe2128c6e126ab30ceafa" + "outcomes/submissions.jsonl": "a829b24e4a03150ab33e3a748a77614c17edf29aa2ae11a118d4e41882c40d4d" }, - "generation": 37913, - "phase": "cycle", + "generation": 37914, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-26T05:04:41.194981+00:00", + "updatedAt": "2026-10-26T05:06:13.476585+00:00", "writerId": "dffce16061d848e398e5b5b22f649ccc" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index da3770b725..194da75d48 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1080,13 +1080,13 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-26T05:02:56.977971+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.787, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125731418, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14125731418}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T21:02:55.262484+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5790047", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-26T05:02:56.977942+00:00", "modelId": "cyankiwi/Hermes-4.3-36B-AWQ-8bit", "modelProfile": {"architectures": ["SeedOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39901408344, "estimatedRequiredGiB": 44.607, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "seed_oss", "modelscopeFileSize": 39913484098, "modelscopeLicense": "apache-2.0", "modelscopeParams": 36151104512, "modelscopeTags": ["license:apache-2.0", "model_type:seed_oss", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Bytedance Seed", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 39913484098}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T21:02:55.274300+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5790051", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-26T05:02:56.977854+00:00", "modelId": "IFM/Jais-3-3.7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6342166448, "estimatedRequiredGiB": 7.112, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6363495404, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5058255360, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:3.7B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2, "参数/模板问题": 2}, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-24T18:37:46.581678+00:00", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 6363495404}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T21:02:55.275701+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5790049", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/Trinity-Mini-AWQ-4bit", "modelProfile": {"architectures": ["AfmoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16347953480, "estimatedRequiredGiB": 18.29, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "afmoe", "modelscopeFileSize": 16366038400, "modelscopeLicense": "other", "modelscopeParams": 26123974400, "modelscopeTags": ["license:other", "model_type:afmoe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 16366038400}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T21:04:40.060189+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5790148", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432697392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-25T04:12:56.440372+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 5432697392}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T21:04:40.062353+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790145", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "IFM/Jais-3-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.377, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11074974122, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:7B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11074974122}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T21:04:40.070512+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790147", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "IFM/Jais-3-3.7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6342166448, "estimatedRequiredGiB": 7.112, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6363495404, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5058255360, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:3.7B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6363495404}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T21:04:40.067620+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790146", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "hf/BennyDaBall-Mistral-44B-MoE-Patched-MLX-4bit-G64", "modelProfile": {"architectures": ["MixtralForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24879965466, "estimatedRequiredGiB": 27.828, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mixtral", "modelscopeFileSize": 24900156010, "modelscopeLicense": null, "modelscopeParams": 6911249920, "modelscopeTags": ["model_type:mixtral", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mistral", "custom_tag:moe", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:g64", "custom_tag:patched", "custom_tag:language-model", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24900156010}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T21:04:40.066494+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790144", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24682886272, "estimatedRequiredGiB": 27.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 24697709852, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 24697709852}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T21:05:33.552384+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790178", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/DASD-4B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432701212, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-25T04:12:56.440372+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 5432701212}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T21:05:33.562829+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790179", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-26T05:06:12.366370+00:00", "modelId": "cyankiwi/Trinity-Mini-AWQ-4bit", "modelProfile": {"architectures": ["AfmoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16347953480, "estimatedRequiredGiB": 18.29, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "afmoe", "modelscopeFileSize": 16366038400, "modelscopeLicense": "other", "modelscopeParams": 26123974400, "modelscopeTags": ["license:other", "model_type:afmoe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 16366038400}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T21:04:40.060189+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5790148", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-26T05:06:12.366355+00:00", "modelId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432697392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-25T04:12:56.440372+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 5432697392}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T21:04:40.062353+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790145", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-26T05:06:12.366382+00:00", "modelId": "IFM/Jais-3-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.377, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11074974122, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:7B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11074974122}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T21:04:40.070512+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790147", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-26T05:06:12.366321+00:00", "modelId": "IFM/Jais-3-3.7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6342166448, "estimatedRequiredGiB": 7.112, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6363495404, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5058255360, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:3.7B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6363495404}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T21:04:40.067620+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790146", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-26T05:06:12.366347+00:00", "modelId": "hf/BennyDaBall-Mistral-44B-MoE-Patched-MLX-4bit-G64", "modelProfile": {"architectures": ["MixtralForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24879965466, "estimatedRequiredGiB": 27.828, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mixtral", "modelscopeFileSize": 24900156010, "modelscopeLicense": null, "modelscopeParams": 6911249920, "modelscopeTags": ["model_type:mixtral", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mistral", "custom_tag:moe", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:g64", "custom_tag:patched", "custom_tag:language-model", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24900156010}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T21:04:40.066494+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790144", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-26T05:06:12.366363+00:00", "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24682886272, "estimatedRequiredGiB": 27.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 24697709852, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 24697709852}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T21:05:33.552384+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790178", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-26T05:06:12.366376+00:00", "modelId": "cyankiwi/DASD-4B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432701212, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-25T04:12:56.440372+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 5432701212}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T21:05:33.562829+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790179", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "kakarotter/calix", "modelProfile": {"architectures": [], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2290347504, "estimatedRequiredGiB": 2.562, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 2292275515, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1145157120, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:pretraining"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2292275515}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T21:24:09.627969+00:00", "targetGpu": "Vastai_va16", "taskId": "5790451", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["Olmo3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35211965376, "estimatedRequiredGiB": 39.364, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "olmo3", "modelscopeFileSize": 35221904676, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32233522176, "modelscopeTags": ["license:apache-2.0", "model_type:olmo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 35221904676}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T21:30:27.259204+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790519", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "IFM/Jais-3-3.7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6342166448, "estimatedRequiredGiB": 7.112, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6363495404, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5058255360, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:3.7B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6363495404}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T21:36:50.963076+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5790605", "taskType": "text-generation", "verifyResult": null}