minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[CPU Doc]Add Xeon CPU info in Qwen3 Cookbook (#25971)

Browse Source
This commit is contained in:
Zaili Wang
2026-05-26 12:14:07 -07:00
committed by GitHub
parent 0753182b50
commit 47617cc4df
2 changed files with 26 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/cookbook/autoregressive/Qwen/Qwen3.mdx
+4 -1
View File
@@ -26,13 +26,15 @@ 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 and AMD GPUs. 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, 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.
@@ -51,6 +53,7 @@ import { Qwen3Deployment } from "/src/snippets/autoregressive/qwen3-deployment.j
- `--speculative-eagle-topk 1`: Top-k sampling for draft tokens
- `--speculative-num-draft-tokens 4`: Number of draft tokens per step
- `--speculative-draft-model-path`: The path of the draft model weights. This can be a local folder or a Hugging Face repo ID such as [`lmsys/SGLang-EAGLE3-Qwen3-235B-A22B-Instruct-2507-SpecForge-Meituan`](https://huggingface.co/lmsys/SGLang-EAGLE3-Qwen3-235B-A22B-Instruct-2507-SpecForge-Meituan).
- For configuring CPU service, please refer to the `Notes` part in the serving engine launching section in [the SGLang CPU server document](../../../docs/hardware-platforms/cpu_server#launch-of-the-serving-engine) to better understand how to configure the arguments, especially for TP (tensor parallel) and NUMA binding settings.
## 4. Model Invocation
docs_new/src/snippets/autoregressive/qwen3-deployment.jsx
+22 -9
View File
@@ -9,7 +9,8 @@ export const Qwen3Deployment = () => {
b200: { tp: 8, ep: 0, bf16: true, fp8: true },
mi300x: { tp: 4, ep: 0, bf16: true, fp8: true },
mi325x: { tp: 4, ep: 0, bf16: true, fp8: true },
mi355x: { tp: 4, ep: 0, bf16: true, fp8: true }
mi355x: { tp: 4, ep: 0, bf16: true, fp8: true },
xeon: { tp: 6, ep: 0, bf16: true, fp8: true }
},
'30b': {
baseName: '30B-A3B',
@@ -19,7 +20,8 @@ export const Qwen3Deployment = () => {
b200: { tp: 1, ep: 0, bf16: true, fp8: true },
mi300x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi325x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true }
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true },
xeon: { tp: 3, ep: 0, bf16: true, fp8: true }
},
'32b': {
baseName: '32B',
@@ -29,7 +31,8 @@ export const Qwen3Deployment = () => {
b200: { tp: 1, ep: 0, bf16: true, fp8: true },
mi300x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi325x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true }
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true },
xeon: { tp: 6, ep: 0, bf16: true, fp8: true }
},
'14b': {
baseName: '14B',
@@ -39,7 +42,8 @@ export const Qwen3Deployment = () => {
b200: { tp: 1, ep: 0, bf16: true, fp8: true },
mi300x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi325x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true }
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true },
xeon: { tp: 3, ep: 0, bf16: true, fp8: true }
},
'8b': {
baseName: '8B',
@@ -49,7 +53,8 @@ export const Qwen3Deployment = () => {
b200: { tp: 1, ep: 0, bf16: true, fp8: true },
mi300x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi325x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true }
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true },
xeon: { tp: 3, ep: 0, bf16: true, fp8: true }
},
'4b': {
baseName: '4B',
@@ -59,7 +64,8 @@ export const Qwen3Deployment = () => {
b200: { tp: 1, ep: 0, bf16: true, fp8: true },
mi300x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi325x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true }
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true },
xeon: { tp: 3, ep: 0, bf16: true, fp8: true }
},
'1.7b': {
baseName: '1.7B',
@@ -69,7 +75,8 @@ export const Qwen3Deployment = () => {
b200: { tp: 1, ep: 0, bf16: true, fp8: true },
mi300x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi325x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true }
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true },
xeon: { tp: 3, ep: 0, bf16: true, fp8: true }
},
'0.6b': {
baseName: '0.6B',
@@ -79,7 +86,8 @@ export const Qwen3Deployment = () => {
b200: { tp: 1, ep: 0, bf16: true, fp8: true },
mi300x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi325x: { tp: 1, ep: 0, bf16: true, fp8: true },
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true }
mi355x: { tp: 1, ep: 0, bf16: true, fp8: true },
xeon: { tp: 3, ep: 0, bf16: true, fp8: true }
}
};
@@ -94,7 +102,8 @@ export const Qwen3Deployment = () => {
{ id: 'h200', label: 'H200', default: false },
{ id: 'mi300x', label: 'MI300X', default: false },
{ id: 'mi325x', label: 'MI325X', default: false },
{ id: 'mi355x', label: 'MI355X', default: false }
{ id: 'mi355x', label: 'MI355X', default: false },
{ id: 'xeon', label: 'XEON', default: false }
]
},
modelsize: {
@@ -261,6 +270,10 @@ export const Qwen3Deployment = () => {
let cmd = 'python -m sglang.launch_server \\\n';
cmd += ` --model ${modelName}`;
if (hardware === 'xeon') {
cmd += ` \\\n --device cpu \\\n --disable-overlap-schedule`;
}
if (hwConfig.tp > 1) {
cmd += ` \\\n --tp ${hwConfig.tp}`;
}