https://cookbook.sglang.io/docs/cookbook/autoregressive/DeepSeek/DeepSeek-OCR 2026-02-04T05:00:33.552Z https://cookbook.sglang.io/docs/cookbook/autoregressive/DeepSeek/DeepSeek-R1 2026-02-04T05:00:33.551Z https://cookbook.sglang.io/docs/cookbook/autoregressive/DeepSeek/DeepSeek-V3 2026-02-04T05:00:33.555Z https://cookbook.sglang.io/docs/cookbook/autoregressive/DeepSeek/DeepSeek-V3_1 2026-02-04T05:00:37.665Z https://cookbook.sglang.io/docs/cookbook/autoregressive/DeepSeek/DeepSeek-V3_2 2026-02-04T05:00:37.372Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Ernie/Ernie4.5 2026-02-04T05:00:37.369Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Ernie/Ernie4.5-VL 2026-02-04T05:00:37.532Z https://cookbook.sglang.io/docs/cookbook/autoregressive/FlashLabs/Chroma1.0 2026-02-04T05:00:37.505Z https://cookbook.sglang.io/docs/cookbook/autoregressive/GLM/GLM-4.5 2026-02-04T05:00:37.398Z https://cookbook.sglang.io/docs/cookbook/autoregressive/GLM/GLM-4.5V 2026-02-04T05:00:37.562Z https://cookbook.sglang.io/docs/cookbook/autoregressive/GLM/GLM-4.6 2026-02-04T05:00:37.581Z https://cookbook.sglang.io/docs/cookbook/autoregressive/GLM/GLM-4.6V 2026-02-04T05:00:37.371Z https://cookbook.sglang.io/docs/cookbook/autoregressive/GLM/GLM-4.7 2026-02-04T05:00:43.034Z https://cookbook.sglang.io/docs/cookbook/autoregressive/GLM/GLM-4.7-Flash 2026-02-04T05:00:37.480Z https://cookbook.sglang.io/docs/cookbook/autoregressive/GLM/GLM-Glyph 2026-02-04T05:00:43.023Z https://cookbook.sglang.io/docs/cookbook/autoregressive/InternLM/Intern-S1 2026-02-04T05:00:43.015Z https://cookbook.sglang.io/docs/cookbook/autoregressive/InternVL/InternVL3.5 2026-02-04T05:00:43.014Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Jina/Jina-reranker-m0 2026-02-04T05:00:43.019Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Llama/Llama3.1 2026-02-04T05:00:43.024Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Llama/Llama3.3-70B 2026-02-04T05:00:43.014Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Llama/Llama4-Scout 2026-02-04T05:00:43.011Z https://cookbook.sglang.io/docs/cookbook/autoregressive/MiniMax/MiniMax-M2 2026-02-04T05:00:43.013Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Mistral/Devstral-2 2026-02-04T05:00:43.012Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Mistral/Mistral-3 2026-02-04T05:00:47.532Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Moonshotai/Kimi-K2 2026-02-04T05:00:47.535Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Moonshotai/Kimi-Linear 2026-02-04T05:00:47.528Z https://cookbook.sglang.io/docs/cookbook/autoregressive/NVIDIA/Nemotron3-Nano 2026-02-04T05:00:47.536Z https://cookbook.sglang.io/docs/cookbook/autoregressive/OpenAI/GPT-OSS 2026-02-04T05:00:47.556Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Qwen/Qwen2.5-VL 2026-02-04T05:00:47.535Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Qwen/Qwen3 2026-02-04T05:00:47.524Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Qwen/Qwen3-Coder-480B-A35B 2026-02-04T05:00:47.533Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Qwen/Qwen3-Next 2026-02-04T05:00:47.525Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Qwen/Qwen3-VL 2026-02-04T05:00:47.523Z https://cookbook.sglang.io/docs/cookbook/autoregressive/Xiaomi/MiMo-V2-Flash 2026-02-04T05:00:52.387Z https://cookbook.sglang.io/docs/cookbook/base/benchmarks/autoregressive_model_benchmark 2026-02-04T05:00:52.391Z https://cookbook.sglang.io/docs/cookbook/base/benchmarks/diffusion_model_benchmark 2026-02-04T05:00:52.394Z https://cookbook.sglang.io/docs/cookbook/base/reference/server_arguments 2026-02-04T05:00:52.393Z https://cookbook.sglang.io/docs/cookbook/diffusion/FLUX/FLUX 2026-02-04T05:00:52.403Z https://cookbook.sglang.io/docs/cookbook/diffusion/Qwen-Image/Qwen-Image 2026-02-04T05:00:52.401Z https://cookbook.sglang.io/docs/cookbook/diffusion/Qwen-Image/Qwen-Image-Edit 2026-02-04T05:00:52.411Z https://cookbook.sglang.io/docs/cookbook/diffusion/Wan/Wan2.1 2026-02-04T05:00:52.388Z https://cookbook.sglang.io/docs/cookbook/diffusion/Wan/Wan2.2 2026-02-04T05:00:52.389Z https://cookbook.sglang.io/docs/cookbook/diffusion/Z-Image/Z-Image-Turbo 2026-02-04T05:00:55.851Z https://cookbook.sglang.io/docs/cookbook/intro 2026-02-04T05:00:55.857Z https://cookbook.sglang.io/docs/cookbook/specbundle/specbundle_usage 2026-02-04T05:00:55.856Z https://cookbook.sglang.io/docs/cookbook/specbundle/supported_models 2026-02-04T05:00:55.853Z https://cookbook.sglang.io/docs/documentation/advanced_features/attention_backend 2026-02-04T05:00:58.060Z https://cookbook.sglang.io/docs/documentation/advanced_features/checkpoint_engine 2026-02-04T05:00:58.050Z https://cookbook.sglang.io/docs/documentation/advanced_features/cuda_graph_for_multi_modal_encoder 2026-02-04T05:00:58.051Z https://cookbook.sglang.io/docs/documentation/advanced_features/deterministic_inference 2026-02-04T05:00:58.052Z https://cookbook.sglang.io/docs/documentation/advanced_features/dp_for_multi_modal_encoder 2026-02-04T05:00:58.055Z https://cookbook.sglang.io/docs/documentation/advanced_features/epd_disaggregation 2026-02-04T05:00:58.054Z https://cookbook.sglang.io/docs/documentation/advanced_features/expert_parallelism 2026-02-04T05:00:58.057Z https://cookbook.sglang.io/docs/documentation/advanced_features/hicache_best_practices 2026-02-04T05:01:00.762Z https://cookbook.sglang.io/docs/documentation/advanced_features/hicache_design 2026-02-04T05:01:00.756Z https://cookbook.sglang.io/docs/documentation/advanced_features/hicache_storage_runtime_attach_detach 2026-02-04T05:01:00.758Z https://cookbook.sglang.io/docs/documentation/advanced_features/hyperparameter_tuning 2026-02-04T05:01:00.754Z https://cookbook.sglang.io/docs/documentation/advanced_features/lora 2026-02-04T05:01:00.757Z https://cookbook.sglang.io/docs/documentation/advanced_features/observability 2026-02-04T05:01:00.755Z https://cookbook.sglang.io/docs/documentation/advanced_features/pd_disaggregation 2026-02-04T05:01:00.759Z https://cookbook.sglang.io/docs/documentation/advanced_features/pipeline_parallelism 2026-02-04T05:01:00.756Z https://cookbook.sglang.io/docs/documentation/advanced_features/quantization 2026-02-04T05:01:00.765Z https://cookbook.sglang.io/docs/documentation/advanced_features/quantized_kv_cache 2026-02-04T05:01:00.760Z https://cookbook.sglang.io/docs/documentation/advanced_features/separate_reasoning 2026-02-04T05:01:04.223Z https://cookbook.sglang.io/docs/documentation/advanced_features/server_arguments 2026-02-04T05:01:04.225Z https://cookbook.sglang.io/docs/documentation/advanced_features/sgl_model_gateway 2026-02-04T05:01:04.216Z https://cookbook.sglang.io/docs/documentation/advanced_features/sglang_for_rl 2026-02-04T05:01:04.220Z https://cookbook.sglang.io/docs/documentation/advanced_features/speculative_decoding 2026-02-04T05:01:04.218Z https://cookbook.sglang.io/docs/documentation/advanced_features/structured_outputs 2026-02-04T05:01:04.221Z https://cookbook.sglang.io/docs/documentation/advanced_features/structured_outputs_for_reasoning_models 2026-02-04T05:01:04.219Z https://cookbook.sglang.io/docs/documentation/advanced_features/tool_parser 2026-02-04T05:01:04.217Z https://cookbook.sglang.io/docs/documentation/advanced_features/vlm_query 2026-02-04T05:01:04.220Z https://cookbook.sglang.io/docs/documentation/basic_usage/deepseek_v3 2026-02-04T05:01:11.911Z https://cookbook.sglang.io/docs/documentation/basic_usage/deepseek_v32 2026-02-04T05:01:12.136Z https://cookbook.sglang.io/docs/documentation/basic_usage/glm45 2026-02-04T05:01:11.901Z https://cookbook.sglang.io/docs/documentation/basic_usage/glmv 2026-02-04T05:01:12.151Z https://cookbook.sglang.io/docs/documentation/basic_usage/gpt_oss 2026-02-04T05:01:11.899Z https://cookbook.sglang.io/docs/documentation/basic_usage/kimi_k2_5 2026-02-04T05:01:11.910Z https://cookbook.sglang.io/docs/documentation/basic_usage/llama4 2026-02-04T05:01:11.898Z https://cookbook.sglang.io/docs/documentation/basic_usage/minimax_m2 2026-02-04T05:01:11.907Z https://cookbook.sglang.io/docs/documentation/basic_usage/native_api 2026-02-04T05:01:11.900Z https://cookbook.sglang.io/docs/documentation/basic_usage/offline_engine_api 2026-02-04T05:01:11.905Z https://cookbook.sglang.io/docs/documentation/basic_usage/ollama_api 2026-02-04T05:01:15.731Z https://cookbook.sglang.io/docs/documentation/basic_usage/openai_api_completions 2026-02-04T05:01:15.728Z https://cookbook.sglang.io/docs/documentation/basic_usage/openai_api_embeddings 2026-02-04T05:01:15.725Z https://cookbook.sglang.io/docs/documentation/basic_usage/openai_api_vision 2026-02-04T05:01:15.722Z https://cookbook.sglang.io/docs/documentation/basic_usage/qwen3 2026-02-04T05:01:15.726Z https://cookbook.sglang.io/docs/documentation/basic_usage/qwen3_vl 2026-02-04T05:01:15.719Z https://cookbook.sglang.io/docs/documentation/basic_usage/sampling_params 2026-02-04T05:01:15.720Z https://cookbook.sglang.io/docs/documentation/basic_usage/send_request 2026-02-04T05:01:15.718Z https://cookbook.sglang.io/docs/documentation/developer_guide/JIT_kernels 2026-02-04T05:01:19.958Z https://cookbook.sglang.io/docs/documentation/developer_guide/bench_serving 2026-02-04T05:01:19.965Z https://cookbook.sglang.io/docs/documentation/developer_guide/benchmark_and_profiling 2026-02-04T05:01:20.356Z https://cookbook.sglang.io/docs/documentation/developer_guide/contribution_guide 2026-02-04T05:01:19.964Z https://cookbook.sglang.io/docs/documentation/developer_guide/development_guide_using_docker 2026-02-04T05:01:19.961Z https://cookbook.sglang.io/docs/documentation/developer_guide/evaluating_new_models 2026-02-04T05:01:19.962Z https://cookbook.sglang.io/docs/documentation/get_started/install 2026-02-04T05:01:20.336Z https://cookbook.sglang.io/docs/documentation/introduction 2026-02-04T05:01:20.256Z https://cookbook.sglang.io/docs/documentation/platforms/amd_gpu 2026-02-04T05:01:23.429Z https://cookbook.sglang.io/docs/documentation/platforms/ascend_contribution_guide 2026-02-04T05:01:23.442Z https://cookbook.sglang.io/docs/documentation/platforms/ascend_npu 2026-02-04T05:01:23.430Z https://cookbook.sglang.io/docs/documentation/platforms/ascend_npu_best_practice 2026-02-04T05:01:23.485Z https://cookbook.sglang.io/docs/documentation/platforms/ascend_npu_deepseek_example 2026-02-04T05:01:23.471Z https://cookbook.sglang.io/docs/documentation/platforms/ascend_npu_qwen3_examples 2026-02-04T05:01:23.438Z https://cookbook.sglang.io/docs/documentation/platforms/ascend_npu_support_models 2026-02-04T05:01:23.462Z https://cookbook.sglang.io/docs/documentation/platforms/cpu_server 2026-02-04T05:01:23.431Z https://cookbook.sglang.io/docs/documentation/platforms/nvidia_jetson 2026-02-04T05:01:29.964Z https://cookbook.sglang.io/docs/documentation/platforms/tpu 2026-02-04T05:01:29.960Z https://cookbook.sglang.io/docs/documentation/platforms/xpu 2026-02-04T05:01:29.961Z https://cookbook.sglang.io/docs/documentation/references/custom_chat_template 2026-02-04T05:01:29.963Z https://cookbook.sglang.io/docs/documentation/references/environment_variables 2026-02-04T05:01:29.966Z https://cookbook.sglang.io/docs/documentation/references/faq 2026-02-04T05:01:29.967Z https://cookbook.sglang.io/docs/documentation/references/frontend/choices_methods 2026-02-04T05:01:29.969Z https://cookbook.sglang.io/docs/documentation/references/frontend/frontend_tutorial 2026-02-04T05:01:29.965Z https://cookbook.sglang.io/docs/documentation/references/learn_more 2026-02-04T05:01:32.888Z https://cookbook.sglang.io/docs/documentation/references/multi_node_deployment/deploy_on_k8s 2026-02-04T05:01:32.881Z https://cookbook.sglang.io/docs/documentation/references/multi_node_deployment/lws_pd/lws_pd_deploy 2026-02-04T05:01:32.880Z https://cookbook.sglang.io/docs/documentation/references/multi_node_deployment/multi_node 2026-02-04T05:01:32.884Z https://cookbook.sglang.io/docs/documentation/references/multi_node_deployment/rbg_pd/deepseekv32_pd 2026-02-04T05:01:32.879Z https://cookbook.sglang.io/docs/documentation/references/post_training_integration 2026-02-04T05:01:32.883Z https://cookbook.sglang.io/docs/documentation/references/production_metrics 2026-02-04T05:01:32.882Z https://cookbook.sglang.io/docs/documentation/references/production_request_trace 2026-02-04T05:01:32.885Z https://cookbook.sglang.io/docs/documentation/supported_models/classify_models 2026-02-04T05:01:36.652Z https://cookbook.sglang.io/docs/documentation/supported_models/diffusion_language_models 2026-02-04T05:01:36.648Z https://cookbook.sglang.io/docs/documentation/supported_models/diffusion_models 2026-02-04T05:01:36.682Z https://cookbook.sglang.io/docs/documentation/supported_models/embedding_models 2026-02-04T05:01:36.961Z https://cookbook.sglang.io/docs/documentation/supported_models/generative_models 2026-02-04T05:01:36.659Z https://cookbook.sglang.io/docs/documentation/supported_models/mindspore_models 2026-02-04T05:01:36.644Z https://cookbook.sglang.io/docs/documentation/supported_models/modelscope 2026-02-04T05:01:36.644Z https://cookbook.sglang.io/docs/documentation/supported_models/multimodal_language_models 2026-02-04T05:01:36.660Z https://cookbook.sglang.io/docs/documentation/supported_models/rerank_models 2026-02-04T05:01:36.888Z https://cookbook.sglang.io/docs/documentation/supported_models/reward_models 2026-02-04T05:01:36.650Z https://cookbook.sglang.io/docs/documentation/supported_models/support_new_models 2026-02-04T05:01:41.650Z https://cookbook.sglang.io/docs/documentation/supported_models/transformers_fallback 2026-02-04T05:01:41.638Z