ai-agent

vllm-ascend: Accelerate LLM Inference on Ascend Hardware

Leverage vllm-ascend to run large language models efficiently on Ascend GPUs, cutting latency and cost. Ideal for AI startups needing high‑performance serving (2.9k+ GitHub stars).

From the repo · “Community maintained hardware plugin for vLLM on Huawei Ascend”

intermediate⏱ 30 minutes💵 Free
3,000 stars+10★ this week2,486 forksPythonGuide quality 8/10 · reviewed Oct 7Updated 10/22/2026100% free · open source
What it is

Use vLLM on Ascend hardware for fast and efficient AI operations.

Real use case example

"A founder, Alex, needs to automate welcome emails for new customers on their e-commerce site. They use vLLM on Ascend to create an automation that checks for new sign-ups, creates a new contact in Salesforce, and sends a welcome email. This automation frees up time for Alex to focus on growing the business. This automation works in 5 minutes."

Best insideClaude Desktop
When to use it
  • •When you need to optimize vLLM performance on Ascend hardware
  • •When integrating open-source plugins for custom AI applications
  • •When developing AI-powered products requiring community-driven hardware support
Ready-to-paste prompt
To build and run a custom vLLM plugin, use `mkdir build && cd build && cmake .. && make`, then integrate the compiled plugin into your Ascend project
Heads up: Ensure you have a compatible C++ compiler and necessary development libraries installed on your system, as the vllm-ascend project requires compiling C++ code and may have specific version requirements
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/vllm-ascend && curl -fsSL https://workflowstacks.com/api/skills/vllm-ascend/claude-skill -o ~/.claude/skills/vllm-ascend/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

37
top-level files
13
folders
119.5M
source size
Apache-2.0
license
Key files
.pre-commit-config.yaml
AGENTS.md
README.md
README.zh.md
requirements-dev.txt
requirements-lint.txt
File tree
.agents/
.claude/
.gemini/
.github/
benchmarks/
cmake/
csrc/
docs/
examples/
release_notes/
tests/
tools/
vllm_ascend/
.clang-format
.gitignore
.gitleaks.toml
.gitmodules
.markdownlint.yaml
.pre-commit-config.yaml
.readthedocs.yaml
AGENTS.md
CLAUDE.md
CMakeLists.txt
CODE_OF_CONDUCT.md
Quick Actions
Details
Creator
vllm-project
Language
Python
Category
ai-agent
Published
1/29/2025

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/vllm-ascend.svg)](https://workflowstacks.com/skills/vllm-ascend?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.