diff --git a/docs/cookbook/autoregressive/DeepSeek/DeepSeek-OCR-2.mdx b/docs/cookbook/autoregressive/DeepSeek/DeepSeek-OCR-2.mdx index cfe54990b..3aa56939e 100644 --- a/docs/cookbook/autoregressive/DeepSeek/DeepSeek-OCR-2.mdx +++ b/docs/cookbook/autoregressive/DeepSeek/DeepSeek-OCR-2.mdx @@ -30,15 +30,15 @@ For more details, please refer to the [official DeepSeek-OCR-2 repository](https Please refer to the [official SGLang installation guide](../../../docs/get-started/install) for installation instructions. -For SGLang CPU installation, please refer to the [CPU version installation guide](../../../docs/hardware-platforms/cpu_server#installation). - ## 3. Model Deployment This section provides deployment configurations optimized for different hardware platforms and use cases. ### 3.1 Basic Configuration -**Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your hardware platform, quantization method, and deployment strategy. SGLang supports serving DeepSeek-OCR-2 on NVIDIA H200 and B200, AMD MI300X, MI355X, and MI325X GPUs, as well as Intel Xeon CPUs. +The DeepSeek-OCR-2 series offers models in various sizes and architectures, optimized for different hardware platforms including NVIDIA GPUs, AMD GPUs, Intel Arc Pro B-Series GPUs(codename: BMG (Battlemage)), and Intel Xeon CPUs. The recommended launch configurations vary by hardware and model size. + +**Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your hardware platform, quantization method, and deployment strategy. SGLang supports serving DeepSeek-OCR-2 on NVIDIA H200 and B200, AMD MI300X, MI355X, and MI325X GPUs, and Intel Arc Pro B-Series GPUs, as well as Intel Xeon CPUs. diff --git a/docs/cookbook/autoregressive/Google/Gemma4.mdx b/docs/cookbook/autoregressive/Google/Gemma4.mdx index a1e4ef921..81f549969 100644 --- a/docs/cookbook/autoregressive/Google/Gemma4.mdx +++ b/docs/cookbook/autoregressive/Google/Gemma4.mdx @@ -97,6 +97,8 @@ For other installation methods, please refer to the [official SGLang installatio ### 3.1 Basic Configuration +The Gemma 4 series offers models in various sizes and architectures, optimized for different hardware platforms including NVIDIA GPUs, AMD GPUs, and Intel Arc Pro B-Series GPUs(codename: BMG (Battlemage)). The recommended launch configurations vary by hardware and model size. + **Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your hardware platform and model variant. diff --git a/docs/cookbook/autoregressive/Meta/Llama3.1.mdx b/docs/cookbook/autoregressive/Meta/Llama3.1.mdx index 8827abf67..2bccc224e 100644 --- a/docs/cookbook/autoregressive/Meta/Llama3.1.mdx +++ b/docs/cookbook/autoregressive/Meta/Llama3.1.mdx @@ -22,11 +22,9 @@ SGLang offers multiple installation methods. You can choose the most suitable in Please refer to the [official SGLang installation guide](../../../docs/get-started/install) for installation instructions. -For SGLang CPU installation, please refer to the [CPU version installation guide](../../../docs/hardware-platforms/cpu_server#installation). - ## 3. Model Deployment -This section provides deployment configurations optimized for different hardware platforms and use cases. +This section provides deployment configurations optimized for different hardware platforms including NVIDIA GPUs, AMD GPUs, Intel Arc Pro B-Series GPUs(codename: BMG (Battlemage)), and Intel Xeon CPUs. ### 3.1 Basic Configuration diff --git a/docs/cookbook/autoregressive/Meta/Llama3.3-70B.mdx b/docs/cookbook/autoregressive/Meta/Llama3.3-70B.mdx index 549ca1a8d..ebceaa55f 100644 --- a/docs/cookbook/autoregressive/Meta/Llama3.3-70B.mdx +++ b/docs/cookbook/autoregressive/Meta/Llama3.3-70B.mdx @@ -24,15 +24,13 @@ For more details, please refer to the [official Llama models repository](https:/ Please refer to the [official SGLang installation guide](../../../docs/get-started/install) for installation instructions. -For SGLang CPU installation, please refer to the [CPU version installation guide](../../../docs/hardware-platforms/cpu_server#installation). - ## 3. Model Deployment -This section provides deployment configurations optimized for AMD GPUs (MI300X, MI325X, MI355X) and Intel Xeon CPUs. +This section provides deployment configurations optimized for AMD GPUs (MI300X, MI325X, MI355X), Intel Arc Pro B-Series GPUs(codename: BMG (Battlemage)) and Intel Xeon CPUs. ### 3.1 Interactive Configuration -**Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your AMD GPU setup. +**Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your AMD GPU, Intel Arc Pro B-Series GPUs or Intel Xeon CPUs setup. import { Llama33Deployment } from "/src/snippets/autoregressive/llama33-70b-deployment.jsx"; diff --git a/docs/cookbook/autoregressive/NVIDIA/Nemotron3-Nano.mdx b/docs/cookbook/autoregressive/NVIDIA/Nemotron3-Nano.mdx index ee60b6c92..7ec09ef40 100644 --- a/docs/cookbook/autoregressive/NVIDIA/Nemotron3-Nano.mdx +++ b/docs/cookbook/autoregressive/NVIDIA/Nemotron3-Nano.mdx @@ -31,6 +31,8 @@ This section provides a progressive guide from quick deployment to performance t ### 3.1 Basic Configuration +The Nemotron3-Nano series offers models in various sizes and architectures, optimized for different hardware platforms including NVIDIA GPUs and Intel Arc Pro B-Series GPUs(codename: BMG (Battlemage)). + **Interactive Command Generator**: select hardware, model variant, and common knobs to generate a launch command. diff --git a/docs/cookbook/autoregressive/Qwen/Qwen3.5.mdx b/docs/cookbook/autoregressive/Qwen/Qwen3.5.mdx index f61d0513d..8750c7d1e 100644 --- a/docs/cookbook/autoregressive/Qwen/Qwen3.5.mdx +++ b/docs/cookbook/autoregressive/Qwen/Qwen3.5.mdx @@ -111,11 +111,9 @@ docker pull lmsysorg/sglang-rocm:v0.5.19-rocm720-mi35x-20260911 For the full Docker setup and other installation methods, please refer to the [official SGLang installation guide](../../../docs/get-started/install). -For SGLang CPU installation, please refer to the [CPU version installation guide](../../../docs/hardware-platforms/cpu_server#installation). - ## 3. Model Deployment -This section provides deployment configurations optimized for different hardware platforms and use cases. +This section provides deployment configurations optimized for different hardware platforms including NVIDIA GPUs, AMD GPUs, Intel Arc Pro B-Series GPUs(codename: BMG (Battlemage)), and Intel Xeon CPUs. ### 3.1 Basic Configuration diff --git a/docs/cookbook/autoregressive/Qwen/Qwen3.mdx b/docs/cookbook/autoregressive/Qwen/Qwen3.mdx index f58397e7d..4e5d64e5e 100644 --- a/docs/cookbook/autoregressive/Qwen/Qwen3.mdx +++ b/docs/cookbook/autoregressive/Qwen/Qwen3.mdx @@ -26,15 +26,13 @@ SGLang offers multiple installation methods. You can choose the most suitable in Please refer to the [official SGLang installation guide](../../../docs/get-started/install) for installation instructions. -For SGLang CPU installation, please refer to the [CPU version installation guide](../../../docs/hardware-platforms/cpu_server#installation). - ## 3. Model Deployment This section provides deployment configurations optimized for different hardware platforms and use cases. ### 3.1 Basic Configuration -The Qwen3 series offers models in various sizes and architectures, optimized for different hardware platforms including NVIDIA GPUs, AMD GPUs, and Intel Xeon CPUs. The recommended launch configurations vary by hardware and model size. +The Qwen3 series offers models in various sizes and architectures, optimized for different hardware platforms including NVIDIA GPUs, AMD GPUs, Intel Arc Pro B-Series GPUs(codename: BMG (Battlemage)), and Intel Xeon CPUs. The recommended launch configurations vary by hardware and model size. **Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your hardware platform, model size, quantization method, and thinking capabilities. diff --git a/docs/cookbook/diffusion/FLUX/FLUX.mdx b/docs/cookbook/diffusion/FLUX/FLUX.mdx index 3c14f419f..78a659abd 100644 --- a/docs/cookbook/diffusion/FLUX/FLUX.mdx +++ b/docs/cookbook/diffusion/FLUX/FLUX.mdx @@ -34,7 +34,7 @@ This section provides deployment configurations optimized for different hardware FLUX models are optimized for high-quality image generation. The recommended launch configurations vary by hardware and model version. -**Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your hardware platform and model version. SGLang supports serving FLUX on NVIDIA B200, H200, H100, and AMD MI355X, MI325X, MI300X GPUs and Ascend A2/A3 Series NPUs. +**Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your hardware platform and model version. SGLang supports serving FLUX on NVIDIA B200, H200, H100, and AMD MI355X, MI325X, MI300X GPUs, Ascend A2, A3 NPUs Series NPUs and Intel Arc B-series graphics(codename: BMG (Battlemage)). diff --git a/docs/cookbook/diffusion/Z-Image/Z-Image-Turbo.mdx b/docs/cookbook/diffusion/Z-Image/Z-Image-Turbo.mdx index 91cdba231..69b3b662c 100644 --- a/docs/cookbook/diffusion/Z-Image/Z-Image-Turbo.mdx +++ b/docs/cookbook/diffusion/Z-Image/Z-Image-Turbo.mdx @@ -29,7 +29,7 @@ This section provides deployment configurations optimized for different hardware Z-Image-Turbo is optimized for high-quality image generation with only 8 inference steps. The recommended launch configurations vary by hardware. -**Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your hardware platform. +**Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your hardware platform and model version. SGLang supports serving Z-Image-Turbo on NVIDIA B200, H200, H100, and AMD MI355X, MI325X, MI300X GPUs, Ascend A2, A3 NPUs and Intel Arc Pro B-Series GPUs(codename: BMG (Battlemage)). diff --git a/docs/docs/hardware-platforms/xpu.mdx b/docs/docs/hardware-platforms/xpu.mdx index 12bd42346..336e22a5a 100644 --- a/docs/docs/hardware-platforms/xpu.mdx +++ b/docs/docs/hardware-platforms/xpu.mdx @@ -7,39 +7,8 @@ The document addresses how to set up the [SGLang](https://github.com/sgl-project Specifically, SGLang is optimized for [Intel® Arc™ Pro B-Series Graphics](https://www.intel.com/content/www/us/en/ark/products/series/242616/intel-arc-pro-b-series-graphics.html) and [ Intel® Arc™ B-Series Graphics](https://www.intel.com/content/www/us/en/ark/products/series/240391/intel-arc-b-series-graphics.html). -## Optimized Model List - -A list of LLMs have been optimized on Intel GPU, and more are on the way: - - - - - - - - - - - - - - - - - - - - - - - - - - -
Model NameBF16
Llama-3.2-3B[meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
Llama-3.1-8B[meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)
Qwen2.5-1.5B[Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B)
- -**Note:** The model identifiers listed in the table above -have been verified on [Intel® Arc™ B580 Graphics](https://www.intel.com/content/www/us/en/products/sku/241598/intel-arc-b580-graphics/specifications.html). +A number of popular LLMs are optimized and run efficiently on XPU, including the most notable open-source models like Llama series, Qwen series, and Diffusion model series like FLUX and Z-Image. +Please check the [SGLang Cookbook pages](https://docs.sglang.io/cookbook/intro) in which the support status and example commands can be found. Quantized MoE models are covered separately in [MXFP4 MoE Quantization](#mxfp4-moe-quantization) below. @@ -85,6 +54,20 @@ pip install -v . --extra-index-url https://download.pytorch.org/whl/xpu ### Install Using Docker +It is recommended to use Docker for setting up the SGLang environment. + +#### Pull from Docker Hub + +Pull the prebuilt docker image of SGLang package releases from `lmsysorg/sglang` repository. +The [XPU image tags](https://hub.docker.com/r/lmsysorg/sglang/tags?name=xpu) end with `xpu` suffix. +The image pulling command is like: + +```bash Command +docker pull lmsysorg/sglang:v0.5.20-xpu +``` + +#### Build from Dockerfile + [The SGLang XPU Dockerfile](https://github.com/sgl-project/sglang/blob/main/docker/xpu.Dockerfile) is provided to facilitate the installation. Replace `` below with your [HuggingFace access token](https://huggingface.co/docs/hub/en/security-tokens). @@ -121,7 +104,6 @@ Example command to launch SGLang serving: sglang serve \ --model-path \ --trust-remote-code \ - --disable-overlap-schedule \ --device xpu \ --host 0.0.0.0 \ --tp 2 \ # using multi GPUs diff --git a/docs/src/snippets/autoregressive/deepseek-ocr-v2-deployment.jsx b/docs/src/snippets/autoregressive/deepseek-ocr-v2-deployment.jsx index a8bfbec9f..2e7cb0670 100644 --- a/docs/src/snippets/autoregressive/deepseek-ocr-v2-deployment.jsx +++ b/docs/src/snippets/autoregressive/deepseek-ocr-v2-deployment.jsx @@ -10,6 +10,7 @@ export const DeepSeekOCR2Deployment = () => { { id: 'mi325x', label: 'MI325X', default: false }, { id: 'mi355x', label: 'MI355X', default: false }, { id: 'xeon', label: 'XEON', default: false }, + { id: 'arc_b', label: 'BMG', default: false }, ] }, quantization: { @@ -25,8 +26,8 @@ export const DeepSeekOCR2Deployment = () => { type: 'checkbox', items: [ { id: 'tp', label: 'TP', subtitle: 'Tensor Parallel', default: true, required: true }, - { id: 'dp', label: 'DP', subtitle: 'Data Parallel', default: false, disabledWhen: (v) => v.hardware === 'xeon', disabledReason: 'Intel Xeon CPUs only support Tensor Parallel (TP)' }, - { id: 'ep', label: 'EP', subtitle: 'Expert Parallel', default: false, disabledWhen: (v) => v.hardware === 'xeon', disabledReason: 'Intel Xeon CPUs only support Tensor Parallel (TP)' } + { id: 'dp', label: 'DP', subtitle: 'Data Parallel', default: false, disabledWhen: (v) => v.hardware === 'xeon' || v.hardware === 'arc_b', disabledReason: 'Only Tensor Parallel (TP) is supported on this hardware' }, + { id: 'ep', label: 'EP', subtitle: 'Expert Parallel', default: false, disabledWhen: (v) => v.hardware === 'xeon' || v.hardware === 'arc_b', disabledReason: 'Only Tensor Parallel (TP) is supported on this hardware' } ] }, }; @@ -42,6 +43,8 @@ export const DeepSeekOCR2Deployment = () => { cmd += ` --model-path ${modelPath}`; if (hardware === 'xeon') { cmd += ` \\\n --device cpu \\\n --disable-overlap-schedule \\\n --trust-remote-code`; + } else if (hardware === 'arc_b') { + cmd += ` \\\n --device xpu`; } cmd += ` \\\n --enable-multimodal`; @@ -272,9 +275,8 @@ export const DeepSeekOCR2Deployment = () => { ) : option.type === 'checkbox' ? ( (option.items || []).map((item) => { const isChecked = (values[option.name] || []).includes(item.id); - const isDisabled = - item.required || - (typeof item.disabledWhen === 'function' && item.disabledWhen(values)); + const dynDisabled = typeof item.disabledWhen === 'function' && item.disabledWhen(values); + const isDisabled = item.required || dynDisabled; return (