From 4f2d190a4bc20452bdb9cceaaaf3f27cc19c9f36 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 20:38:41 +0000 Subject: [PATCH] state: generation 11727 (intent) --- .../architecture_compatibility_blacklist.json | 2 +- .modelhub_state/market_intelligence.json | 2 +- .modelhub_state/official_capabilities.json | 39 ++--- .modelhub_state/outcome_checkpoint.json | 141 +++++++++++++----- .modelhub_state/recovery_intents.jsonl | 2 + manifest.json | 18 +-- outcomes/submissions.jsonl | 2 - 7 files changed, 134 insertions(+), 72 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index e38197dee6..80c6f384dc 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -2850,7 +2850,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-09-21T20:35:46.662371+00:00", + "generatedAt": "2026-09-21T20:38:25.534299+00:00", "summary": { "activeBlockCount": 143, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 3c792171fb..aa08878065 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -434,7 +434,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-09-21T20:37:38.579863+00:00", + "generatedAt": "2026-09-21T20:38:40.410453+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 0f6c61e0c0..4fead340c4 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-09-21T20:37:38.579863+00:00", + "catalogUpdatedAt": "2026-09-21T20:38:40.410453+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-09-21T20:37:38.579863+00:00", + "generatedAt": "2026-09-21T20:38:41.448296+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -415,14 +415,6 @@ ], "updatedAt": "2026-09-21T18:49:58.101837+00:00" }, - "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit|2026-08-26T12:23:32+00:00|Ascend_910-b4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-21T18:49:57.182615+00:00" - }, "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit|2026-08-26T12:23:32+00:00|Iluvatar_bi-150": { "taskTypes": [ "asr", @@ -5199,19 +5191,6 @@ ], "updatedAt": "2026-09-21T18:50:35.624445+00:00" }, - "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4|2026-08-26T12:24:21+00:00|Iluvatar_bi-150": { - "taskTypes": [ - "asr", - "question_answering", - "reinforcement_learning", - "text-generation", - "text-to-image-generation", - "text_classification", - "vision_classification", - "visual-multi-modal" - ], - "updatedAt": "2026-09-21T18:49:56.789875+00:00" - }, "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4|2026-08-26T12:24:21+00:00|hygon_k100-ai": { "taskTypes": [ "text-generation", @@ -5400,6 +5379,18 @@ ], "updatedAt": "2026-09-21T19:05:30.187973+00:00" }, + "https://modelscope.cn/models/prithivMLmods/CEERS-2112-14B-Instruct|2026-09-21T20:38:14+00:00|Mthreads_s4000": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-21T20:38:40.871875+00:00" + }, + "https://modelscope.cn/models/prithivMLmods/CEERS-2112-14B-Instruct|2026-09-21T20:38:14+00:00|hygon_k100-ai": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-21T20:38:41.448296+00:00" + }, "https://modelscope.cn/models/prithivMLmods/Nexus-9B-CodeCore-Merge-GGUF|2026-09-21T18:51:17+00:00|Ascend_910-b3": { "taskTypes": [ "text-generation", @@ -6849,6 +6840,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-09-21T20:37:38.579863+00:00", + "taskTreeUpdatedAt": "2026-09-21T20:38:40.410453+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 9c7d2b8f51..6987263cb2 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-09-21T20:34:21.873332+00:00", - "lastSyncTime": "2026-09-21T20:34:21.547032+00:00", + "generatedAt": "2026-09-21T20:38:25.463942+00:00", + "lastSyncTime": "2026-09-21T20:38:25.158922+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -2977,24 +2977,24 @@ "decisionSuccessRate": 0.0625, "decisionTotal": 32, "failureBreakdown": { - "ambiguous_runtime": 37, + "ambiguous_runtime": 39, "context_length": 3, "framework_architecture_unsupported": 26, "memory_capacity": 1, "参数/模板问题": 8 }, - "failureCount": 75, - "failureRate": 0.974, + "failureCount": 77, + "failureRate": 0.9747, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 2, - "successRate": 0.026, + "successRate": 0.0253, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 77, - "unresolvedFailureCount": 45 + "total": 79, + "unresolvedFailureCount": 47 }, "Ascend_910-b3|vllm|text-generation": { "attributableFailureCount": 68, @@ -5657,7 +5657,7 @@ "decisionSuccessRate": 0.0253, "decisionTotal": 79, "failureBreakdown": { - "ambiguous_runtime": 86, + "ambiguous_runtime": 88, "backend_operator": 1, "context_length": 3, "framework_architecture_unsupported": 66, @@ -5668,18 +5668,18 @@ "tokenizer_compatibility": 1, "参数/模板问题": 27 }, - "failureCount": 191, - "failureRate": 0.9896, + "failureCount": 193, + "failureRate": 0.9897, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 2, - "successRate": 0.0104, - "total": 193, - "unresolvedFailureCount": 113 + "successRate": 0.0103, + "total": 195, + "unresolvedFailureCount": 115 } }, - "generatedAt": "2026-09-21T20:34:21.861695+00:00", + "generatedAt": "2026-09-21T20:38:25.451761+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 99, @@ -5687,7 +5687,7 @@ "decisionSuccessRate": 0.161, "decisionTotal": 118, "failureBreakdown": { - "ambiguous_runtime": 98, + "ambiguous_runtime": 100, "context_length": 3, "framework_architecture_unsupported": 91, "memory_capacity": 2, @@ -5697,15 +5697,15 @@ "日志缺失": 3, "验证失败": 27 }, - "failureCount": 266, - "failureRate": 0.9333, + "failureCount": 268, + "failureRate": 0.9338, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, - "successRate": 0.0667, - "total": 285, - "unresolvedFailureCount": 167 + "successRate": 0.0662, + "total": 287, + "unresolvedFailureCount": 169 }, "Ascend_910-b4": { "attributableFailureCount": 322, @@ -6279,9 +6279,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 2 + "ambiguous_runtime": 3 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "lfm2", @@ -6293,8 +6293,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 3, + "unresolvedFailureCount": 3 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|awq": { "attributableFailureCount": 0, @@ -6389,6 +6389,29 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "modelType": "mistral", + "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 + }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mpt|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, @@ -21581,6 +21604,30 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none|29": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "loadSizeLog2Bucket": 29, + "modelType": "lfm2", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b3", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -21869,6 +21916,30 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors|32": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "loadSizeLog2Bucket": 32, + "modelType": "mistral", + "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 + }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mpt|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -38002,15 +38073,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 16407, - "totalRecords": 16601, + "terminalRecords": 16409, + "totalRecords": 16603, "totals": { "attributableFailureCount": 5918, "decisionFailureRate": 0.8622, "decisionSuccessRate": 0.1378, "decisionTotal": 6864, "failureBreakdown": { - "ambiguous_runtime": 4034, + "ambiguous_runtime": 4036, "architecture_compatibility": 212, "attention_backend": 1, "backend_operator": 104, @@ -38026,31 +38097,31 @@ "日志缺失": 719, "验证失败": 674 }, - "failureCount": 15461, + "failureCount": 15463, "failureRate": 0.9423, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 925, "successCount": 946, "successRate": 0.0577, - "total": 16407, - "unresolvedFailureCount": 8618 + "total": 16409, + "unresolvedFailureCount": 8620 }, "warnings": [ "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -38090,6 +38161,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 16601, + "summarizedRecords": 16603, "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 1c915379d5..845e0d9bce 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2301,6 +2301,8 @@ {"batchId": "b8f80ac596f046d3846295c66a858414", "completedAt": "2026-09-21T20:37:40.129515+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:37:39.015165+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dcd02034b5cd486998caf8c5b8ef5d72", "lastModified": "2026-09-21T20:13:14+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-64-v2", "reason": null, "reconciledAt": "2026-09-21T20:37:41.801802+00:00", "repoId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5007016", "taskType": "text-generation"} {"batchId": "b8f80ac596f046d3846295c66a858414", "completedAt": "2026-09-21T20:37:40.129524+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:37:39.015291+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9d7a0c5a644d4c1eb3334dcbd463db59", "lastModified": "2026-09-21T18:44:33+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "reason": null, "reconciledAt": "2026-09-21T20:37:41.800858+00:00", "repoId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5007017", "taskType": "text-generation"} {"batchId": "b8f80ac596f046d3846295c66a858414", "completedAt": "2026-09-21T20:37:40.129527+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:37:39.015339+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d8497b774dd44118541f78d58bbfeca", "lastModified": "2026-09-21T18:38:06+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-standard-v1_B", "reason": null, "reconciledAt": "2026-09-21T20:37:41.800586+00:00", "repoId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5007018", "taskType": "text-generation"} +{"batchId": "8f8ff460d579419e91b442876a88e1a4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:38:41.542946+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2216f80ca1b64b72beb33dacd1b14002", "lastModified": "2026-09-21T18:45:44+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "repoId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} +{"batchId": "8f8ff460d579419e91b442876a88e1a4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:38:41.543060+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fa5e4b1425284451b498edda50b349b8", "lastModified": "2026-09-21T18:43:38+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g2-v2_C", "repoId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "24082fb4e4bc48b988e1e4deac30068b", "completedAt": "2026-09-21T20:36:17.828196+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:36:00.461127+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7ef98d8672514b6cb8bcf83850090ffe", "repoId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691781+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137064+00:00", "framework": "vllm", "intentId": "64b834dd640742a0b32535bde02b94ad", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691779+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137007+00:00", "framework": "vllm", "intentId": "d6229ef4ac9942078baa35e312133d9d", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index 3f04a8a69a..b633b3483b 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.20.2", "checksums": { ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", - ".modelhub_state/architecture_compatibility_blacklist.json": "689f079948e0213cbf6a6ec33b347478e187044a4318b3d35e544f270e5031c1", + ".modelhub_state/architecture_compatibility_blacklist.json": "77255b20558aff01fabeca952b36ad29ffe50b4a36d4ea0863be1d56ff3dca06", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "de5d692c520cbe1628ae0b40e6f5bbfdd390b25b375251891467ff151d8892ce", - ".modelhub_state/official_capabilities.json": "20ff5f497966a17d8fb7af31c1d2dceca37ef1234d07297d1be25c6be6e91789", - ".modelhub_state/outcome_checkpoint.json": "46b2561d6b3cd6d53c15cc3f6ecd04e222db80779f35b6c1a90c3d097b2d3cb0", + ".modelhub_state/market_intelligence.json": "5933fa076bd6d5b9e3d9d2fde9988f5478d6be4c961df109e0baf17a7081a57a", + ".modelhub_state/official_capabilities.json": "5ee726201d8ebbee2e7177a196ae0d4db964b1d6f4809b89c79048f036c07290", + ".modelhub_state/outcome_checkpoint.json": "f819a866766665c98335c4d01133d7d7da5ae147a41782490ea71136c0ba5f8a", ".modelhub_state/queue_cleanup_latest.json": "f93bde2de8f7cc7073f34b5456a3df43c8f54023eacfce210dc11e227efd469c", ".modelhub_state/recent_outcomes.jsonl": "66d40a9d21096075d50bc8a3aa6f1faa0bfc0a38ea81924b3c6449bfba8cb0ca", ".modelhub_state/recovery_active_tasks.jsonl": "8168827249c1ba0cf26b135a7c02aa572cc66d6fd89bd5fe426ed6dfc307f7b5", - ".modelhub_state/recovery_intents.jsonl": "851f83bda2ecaa1e133f33bb46348da3f104475a4eb60821cec3a3db2d56a3e1", + ".modelhub_state/recovery_intents.jsonl": "2c8af8f087b1842a2ac2e4d2e2360bdbe3e017ff35a514c21a57bb3a2296c8c6", ".modelhub_state/routing_intelligence.json": "e7b05c954cd5a89b0ffb1e038608c33724516f8b4ae4d34ab7f884bc9596649e", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", "ledger/submissions.jsonl": "29a8b283d87215a6c72599d32450fc49acb2ef55057c37e428312ff76c65f1d1", - "outcomes/submissions.jsonl": "8e3601fa11cc1a89aaf454ada7fd776f9482b61eb941db0dd1a30dfeb667a942" + "outcomes/submissions.jsonl": "fbcf67583816da9fa4849033de26b1d693c151970fadfa03c652e8a56d271e3c" }, - "generation": 11726, - "phase": "cycle", + "generation": 11727, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-09-21T20:37:41.969453+00:00", + "updatedAt": "2026-09-21T20:38:41.745878+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 53c5dc376a..7c240b1a15 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -415,12 +415,10 @@ {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:30:54.600131+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16953948786, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16953948786}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.702212+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969574", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:30:54.600066+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299781, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299781}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.749421+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969575", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:30:54.600004+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.579461+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969573", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600433+00:00", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.586939+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969576", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600240+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663410366, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663410366}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.730955+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969577", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600185+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.241562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969620", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600422+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:31.903313+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969626", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600416+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.045316+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969632", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.599928+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.137439+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969642", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600220+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.146902+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969640", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.599986+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.252209+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969648", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600049+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.237107+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969645", "taskType": "text-generation", "verifyResult": null}