Source: https://seerepo.com/uses/apache-tvm-ffi
Markdown source: https://seerepo.com/uses/apache-tvm-ffi.md
Description: 11 public repos that SeeRepo read use apache-tvm-ffi. It's used most with FastAPI, OpenAI, and uvicorn.

# Open source repos that use apache-tvm-ffi

11 public repos that SeeRepo read use apache-tvm-ffi. It's used most with FastAPI, OpenAI, and uvicorn.

## Used most with

- FastAPI: 7 repos
- OpenAI: 6 repos
- uvicorn: 5 repos
- torch: 5 repos
- pyzmq: 5 repos
- NVIDIA: 5 repos
- flashinfer-python: 4 repos
- transformers: 4 repos

## The repos, by stars

1. [vllm-project/vllm](https://seerepo.com/r/vllm-project/vllm): Python · 97,060 stars · 14.7% signed by AI — A high-throughput and memory-efficient inference and serving engine for LLMs
2. [sgl-project/sglang](https://seerepo.com/r/sgl-project/sglang): Python · 39,041 stars · 9.5% signed by AI — SGLang is a high-performance serving framework for large language models and multimodal models.
3. [Dao-AILab/flash-attention](https://seerepo.com/r/Dao-AILab/flash-attention): Python · 25,304 stars · 1.7% signed by AI — Fast and memory-efficient exact attention
4. [mlc-ai/mlc-llm](https://seerepo.com/r/mlc-ai/mlc-llm): Python · 23,302 stars · 0.2% signed by AI — Universal LLM Deployment Engine with ML Compilation
5. [state-spaces/mamba](https://seerepo.com/r/state-spaces/mamba): Python · 18,976 stars · 0.5% signed by AI — Mamba SSM architecture
6. [FlashML-org/FreeToken](https://seerepo.com/r/FlashML-org/FreeToken): Python · 16,785 stars — FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
7. [NVIDIA/TensorRT-LLM](https://seerepo.com/r/NVIDIA/TensorRT-LLM): Python · 15,038 stars · 1.7% signed by AI — TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
8. [OpenPipe/ART](https://seerepo.com/r/OpenPipe/ART): Python · 10,856 stars · 6.6% signed by AI — Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
9. [tile-ai/tilelang](https://seerepo.com/r/tile-ai/tilelang): Python · 8,976 stars · 4.5% signed by AI —  Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
10. [InternLM/lmdeploy](https://seerepo.com/r/InternLM/lmdeploy): Python · 8,149 stars · 1.2% signed by AI — LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
11. [bojieli/ai-infra-book](https://seerepo.com/r/bojieli/ai-infra-book): Python · 8,032 stars · 16.6% signed by AI — 《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验

## Frequently asked questions

### What is the most popular open source repo that uses apache-tvm-ffi?

vllm-project/vllm, with 97,060 stars on GitHub.

The proof: [vllm-project/vllm on GitHub](https://github.com/vllm-project/vllm)

### What other technologies is apache-tvm-ffi used with?

With FastAPI (7), OpenAI (6), uvicorn (5), torch (5), and pyzmq (5), out of the 11 repos that use it.

### What languages are the repos that use apache-tvm-ffi written in?

Python (11).

### How many repos that use apache-tvm-ffi have commits signed by AI?

10 of the 11; the most, bojieli/ai-infra-book, with 16.6% of its commits.

The proof: [the commits each tool signed in bojieli/ai-infra-book](https://seerepo.com/r/bojieli/ai-infra-book/ai)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.
