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

[NPU] [DOC] Add environment prerequisites to model tutorials (#29293)

Browse Source
This commit is contained in:
amote-i
2026-06-26 09:51:06 +08:00
committed by GitHub
parent 6c92f9f328
commit 10ff3c1dcb
14 changed files with 167 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/docs/hardware-platforms/ascend-npus/ascend_npu.mdx
+11
View File
@@ -124,6 +124,17 @@ If you want to use PD disaggregation mode, you need to install MemFabric-Hybrid.
pip install memfabric-hybrid==1.0.8
```
#### MemFabric-zbal
MemFabric-zbal is a Zero Buffer Acceleration Library of high-performance operators for LLM inference and training on Ascend,
accelerating computation by eliminating intermediate memory buffers; it is required only on **aarch64** clusters and is
installed in addition to MemFabric-Hybrid.
```bash Command
# Only needed on aarch64 (arm64) hosts
pip install memfabric-zbal==1.1.1
```
#### Pytorch and Pytorch Framework Adaptor on Ascend
```bash Command
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/deepseek_r1.mdx
+12
View File
@@ -47,6 +47,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/deepseek_v3_2.mdx
+12
View File
@@ -46,6 +46,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/glm_5_1.mdx
+12
View File
@@ -48,6 +48,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/kimi_k2_6.mdx
+12
View File
@@ -48,6 +48,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/minimax_m2_5.mdx
+12
View File
@@ -45,6 +45,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3-8b.mdx
+12
View File
@@ -42,6 +42,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_235b_a22b.mdx
+12
View File
@@ -48,6 +48,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_30b_a3b.mdx
+12
View File
@@ -42,6 +42,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_32b.mdx
+12
View File
@@ -40,6 +40,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_5_397b.mdx
+12
View File
@@ -45,6 +45,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_6_27b.mdx
+12
View File
@@ -42,6 +42,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_6_35b_a3b.mdx
+12
View File
@@ -42,6 +42,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>
docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_next_80b_a3b_instruct.mdx
+12
View File
@@ -44,6 +44,18 @@ see [Feature Compatibility](/docs/hardware-platforms/ascend-npus/ascend_npu_opti
## Prerequisites
### Environment
Before following this tutorial, complete the environment setup in the documents below:
- [Ascend NPU Quickstart](/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start) — the fastest way to get started.
It walks you through launching the official container image, starting the SGLang server, and sending a test request.
Recommended if you are new to SGLang on Ascend.
- [SGLang Installation with NPU Support](/docs/hardware-platforms/ascend-npus/ascend_npu) — the full installation guide.
It covers the component version mapping (CANN, PyTorch adapter, Triton, kernels, etc.), building from source or from a
Dockerfile, and recommended system settings (CPU power scheme, NUMA, swap). Use it when you need to install or customize
the environment instead of using the official image.
### Model weights
<Warning>