workflowstacks

The marketplace for AI skills that launch offers, rank in AI search, and automate operations. No coding required.

๐•โšก๐Ÿ’ฌ

Marketplace

  • Browse Skills
  • AI Agents
  • Claude Skills
  • MCP Servers
  • Prompts

Solutions

  • For Founders
  • For Agencies
  • For Ecommerce
  • Agent Builder
  • Starter Packs
  • Playbooks

Learn

  • How It Works
  • What Are Skills
  • What Are Agents
  • What Is MCP
  • For Creators
  • Submit a Tool
  • Security

Company

  • Become a Creator
  • About
  • Enterprise
  • API Docs
  • Terms
  • Privacy
  • Support
Compatible with
๐Ÿค–ChatGPT
โœจClaude
๐Ÿ’ŽGemini
๐Ÿ›๏ธShopify
๐Ÿ”Ahrefs
๐Ÿ“ŠSheets
๐Ÿ’ฌWhatsApp
๐Ÿ“ฑMeta Ads
+50 moreCreator program โ†’

ยฉ 2026 WorkflowStacks. All rights reserved.

TermsPrivacySupport
ai-agent

xllm: Fast AI Inference

Get high-performance AI model inference with xllm, ideal for startup founders working with large language models, backed by 1.4k+ GitHub stars
1,468 stars256 forksC++Quality 8/10Updated 7/13/2026100% free ยท open source
What it does

xllm provides high-performance inference for large language models, enabling fast and efficient processing of AI workloads

Install / run
git clone https://github.com/xLLM-AI/xllm.git
When to use it
  • โ€ขYou need to deploy large language models in a production environment with strict latency requirements
  • โ€ขYour startup relies on real-time natural language processing for tasks like sentiment analysis or text classification
  • โ€ขYou want to optimize the performance of your AI models on diverse hardware accelerators
Quick start
  1. 1Build the xllm engine using the command 'mkdir build && cd build && cmake .. && make -j'
  2. 2Prepare your model by converting it to the xllm format using the 'xllm_convert' tool
  3. 3Create a configuration file 'config.json' to specify the model and accelerator settings
  4. 4Run the xllm inference engine using the command 'xllm_infer -c config.json -m your_model.xllm'
  5. 5Use the 'xllm_benchmark' tool to evaluate the performance of your model on different hardware accelerators
Ready-to-paste prompt
xllm_infer -c config.json -m your_model.xllm -i 'What is the capital of France?'
Heads up: Ensure you have the necessary dependencies installed, including CMake and a compatible C++ compiler, and that your model is compatible with the xllm format
Saves to your device

Topics

deepseek
glm
inference
inference-engine
large-language-models
llm-inference
qwen
What's inside โ€” free to inspect
No purchase needed

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

17
top-level files
15
folders
26.5M
repo size
Apache-2.0
license
Key files
.pre-commit-config.yaml
AGENTS.md
README_zh.md
README.md
File tree
.agents/
.claude/
.gemini/
.github/
assets/
cibuild/
cmake/
docker/
docs/
examples/
scripts/
tests/
third_party/
tools/
xllm/
.clang-format
.gitignore
.gitmodules
.pre-commit-config.yaml
AGENTS.md
CLAUDE.md
CMakeLists.txt
LICENSE
MANIFEST.in
Quick Actions
Details
Creator
xLLM-AI
Language
C++
Category
ai-agent
Published
8/12/2025

Are you the creator of this tool? Claim your listing โ†’ and earn 85% of every sale.

Related skills

More ai-agent tools founders pair with this one.

ai-agentโ˜… 512,463
build-your-own-x: Learn by Recreating
Improve programming skills by rebuilding tech from scratch. For startup founders and programmers.
ai-agentโ˜… 450,961
Learn to code with freeCodeCamp
Get free programming education with freeCodeCamp, for startup founders and beginners.
ai-agentโ˜… 439,771
Public-apis: Free API Access
Get free APIs for development. For startup founders and developers.
ai-agentโ˜… 390,947
Free Programming Books
Discover free programming books for founders and developers. Learn with free-programming-books.
ai-agentโ˜… 350,624
coding-interview-university: Learn to Code
Get a complete study plan to become a software engineer, for startup founders, with 351k+ GitHub stars
ai-agentโ˜… 297,550
Selfhosted Control with awesome-selfhosted
Host your own network services and web apps. For founders seeking privacy and control.