From 7f256194e2f6782b509df32efab2054d0ab188f1 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 16:21:12 +0000 Subject: [PATCH] state: generation 11550 (result) --- .modelhub_state/recovery_intents.jsonl | 4 ++-- .modelhub_state/routing_intelligence.json | 12 ++++++------ ledger/submissions.jsonl | 2 ++ manifest.json | 14 +++++++------- outcomes/submissions.jsonl | 2 ++ 5 files changed, 19 insertions(+), 15 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 574de9a80f..de1d10c066 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2144,8 +2144,8 @@ {"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557889+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026656+00:00", "framework": "vllm-customized", "intentId": "bae91b55332d49569a09fe8955c567ca", "lastModified": "2026-08-24T19:38:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-21T16:19:52.302965+00:00", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5003541", "taskType": "text-generation"} {"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557917+00:00", "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027216+00:00", "framework": "vllm-customized", "intentId": "1a967a56b6544a418ff853e4c7bfdcc2", "lastModified": "2026-08-26T16:48:25+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "reason": null, "reconciledAt": "2026-09-21T16:19:52.301492+00:00", "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5003581", "taskType": "text-generation"} {"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557919+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027268+00:00", "framework": "vllm", "intentId": "f700a1af5ee74960a2b656f28e6d2d98", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-21T16:19:52.301488+00:00", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5003582", "taskType": "text-generation"} -{"batchId": "1d7f222438574c7bb7d308b0b6ff99a2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:20:53.319844+00:00", "framework": "vllm", "intentId": "df8d2c07bfc9498eb3a577afb8228392", "lastModified": "2026-09-20T14:21:01+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "repoId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "1d7f222438574c7bb7d308b0b6ff99a2", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:20:53.320004+00:00", "framework": "vllm-patch-tokenizer", "intentId": "d51a43dc8a934b9d82753d02071dfdf1", "lastModified": "2026-09-21T15:48:16+00:00", "modelAddress": "https://modelscope.cn/models/amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "repoId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} +{"batchId": "1d7f222438574c7bb7d308b0b6ff99a2", "completedAt": "2026-09-21T16:21:12.536971+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:20:53.319844+00:00", "framework": "vllm", "intentId": "df8d2c07bfc9498eb3a577afb8228392", "lastModified": "2026-09-20T14:21:01+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5003636", "taskType": "text-generation"} +{"batchId": "1d7f222438574c7bb7d308b0b6ff99a2", "completedAt": "2026-09-21T16:21:12.536989+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:20:53.320004+00:00", "framework": "vllm-patch-tokenizer", "intentId": "d51a43dc8a934b9d82753d02071dfdf1", "lastModified": "2026-09-21T15:48:16+00:00", "modelAddress": "https://modelscope.cn/models/amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "reason": null, "repoId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "5003635", "taskType": "text-generation"} {"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557925+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027384+00:00", "framework": "vllm", "intentId": "108b5d7796ff4f7eab76b1d9599f28f8", "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": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557922+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027327+00:00", "framework": "vllm", "intentId": "842fba2048ed4c40851a0d05130be4ef", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557914+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027164+00:00", "framework": "vllm-customized", "intentId": "a7dbd728ea8646b4a0fd2feab9368f6c", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index ce1fde34de..270b35c2b8 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2283 + "unified_success_first": 2285 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -25,7 +25,7 @@ "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 48, "text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 11, "text-generation|Iluvatar_mrv-100|vllm": 63, - "text-generation|Kunlunxin_p-800|vllm": 59, + "text-generation|Kunlunxin_p-800|vllm": 60, "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 183, "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 87, "text-generation|MetaX_c-500|vllm": 104, @@ -36,10 +36,10 @@ "text-generation|Vastai_va16|vllm_fix_tokenizer": 75, "text-generation|hygon_k100-ai|llamacpp": 18, "text-generation|hygon_k100-ai|vllm": 26, - "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 132 + "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 133 }, - "acceptedSinceRefresh": 2283, - "acceptedTotal": 2283, - "generatedAt": "2026-09-21T16:19:49.489409+00:00", + "acceptedSinceRefresh": 2285, + "acceptedTotal": 2285, + "generatedAt": "2026-09-21T16:21:12.452385+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 12b6643a9d..06109340ab 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1221,3 +1221,5 @@ {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "submitTime": "2026-09-21T16:01:28.480821+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003387", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "submitTime": "2026-09-21T16:01:44.276852+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003411", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "submitTime": "2026-09-21T16:04:25.561880+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003413", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-21T16:21:12.358143+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5003636", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"} +{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "submitTime": "2026-09-21T16:21:12.297298+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5003635", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} diff --git a/manifest.json b/manifest.json index 0d61acd4f0..c970ebc0e6 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "0ad8bae3fa1afa7ca210869b402afc058a903fdc4e2d86ace5dcbd51a06fabd1", ".modelhub_state/recent_outcomes.jsonl": "5287587f515a80b0cab742de9c1b977e27211f4f5402df3cbc1d5e80b9cea96b", ".modelhub_state/recovery_active_tasks.jsonl": "b72ab366f89402f9f1529f5c55c91cf45fa145ec87c779bb65f74ba5c4fe9191", - ".modelhub_state/recovery_intents.jsonl": "d163964eee665d70ede2564e85fce0ba75e131d41482cdf163d1ec4ff218bec9", - ".modelhub_state/routing_intelligence.json": "5aac3b30c8d83b88461973730b606a1bb6ccccc53da359db663dc6d9713e3643", + ".modelhub_state/recovery_intents.jsonl": "41bddbfad734baf7be832878670999bfc29cb638fe5b72cb2a7c276648d487c9", + ".modelhub_state/routing_intelligence.json": "217840d12464a08e2c8c9c4b55e6df385c23fbfb79ef358da5fb01fb2bdb7918", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", - "ledger/submissions.jsonl": "db845b426a9aa2d32d2f21962b6b3b5bff03c630a2475ab74d10a8011926d18a", - "outcomes/submissions.jsonl": "12e50028d9d9e4afd091c3903f40e1a2975d6a6fa47441bdc0b8bda6f380d970" + "ledger/submissions.jsonl": "e71d36e686f333f7b7d73f6679311b2dae1f68bd827e6b0052dae40f6a0a1554", + "outcomes/submissions.jsonl": "96c460248b338411ef32acbaaee9640943c81dc8eb8fe40df9fa06faf76b4399" }, - "generation": 11549, - "phase": "intent", + "generation": 11550, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-21T16:20:53.483076+00:00", + "updatedAt": "2026-09-21T16:21:12.672717+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 6fa431e788..d6b52c7074 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1158,3 +1158,5 @@ {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020349648, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022916227, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022916227}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T16:14:31.701642+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5003541", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B-IT", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361928, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008164431, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008164431}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T16:16:37.962127+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5003581", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "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": 17788612744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T16:16:38.115066+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5003582", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T16:21:12.358143+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5003636", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 51304360808, "estimatedRequiredGiB": 57.349, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 51315158961, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 51315158961}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T16:21:12.297298+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5003635", "taskType": "text-generation", "verifyResult": null}