Skip to content

Commit eb81619

Browse files
authored
[Doc][Feature] Add Motor deployment guide (vllm-project#10745)
### What this PR does / why we need it? This PR adds a deployment guide for using MindIE-PyMotor with vLLM-Ascend. MindIE-PyMotor provides one-click deployment for prefill–decode (PD) disaggregation and PD aggregation on Ascend NPUs. ### Does this PR introduce _any_ user-facing change? No, this is a documentation-only update. ### How was this patch tested? Documentation-only change, no testing required. - vLLM version: v0.22.1 - vLLM main: vllm-project/vllm@967c5c3 --------- Signed-off-by: 1478931959 <112932568+1478931959@users.noreply.github.com>
1 parent 2ed6ef0 commit eb81619

2 files changed

Lines changed: 10 additions & 0 deletions

File tree

docs/source/user_guide/deployment_guide/index.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4,4 +4,5 @@
44
:caption: Deployment Guide
55
:maxdepth: 1
66
using_volcano_kthena
7+
using_mindie_pymotor
78
:::
Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
# Deploy vLLM-Ascend with MindIE-PyMotor
2+
3+
## 1. Overview
4+
5+
[MindIE-PyMotor](https://gitcode.com/Ascend/MindIE-PyMotor) provides one-click deployment for **prefill–decode (PD) disaggregation** and **PD aggregation** on Ascend NPUs with vLLM-Ascend. It uses **high-performance scheduling and load balancing**, together with **RAS (Reliability, Availability and Serviceability) capabilities**, to build inference services that are fast and highly stable.
6+
7+
## 2. Getting Started
8+
9+
For quick deployment instructions, refer to the [MindIE-PyMotor Quick Start](https://gitcode.com/Ascend/MindIE-PyMotor/blob/master/docs/zh/user_guide/README.md).

0 commit comments

Comments
 (0)