Source: https://seerepo.com/compare/mlc-ai/mlc-llm/vs/vllm-project/vllm
Markdown source: https://seerepo.com/compare/mlc-ai/mlc-llm/vs/vllm-project/vllm.md
Description: mlc-llm and vllm share 8 technologies: FastAPI, datasets, OpenAI, sentencepiece, transformers, safetensors, tiktoken, and torch. Both are written in Python.

# mlc-llm vs vllm

mlc-llm and vllm share 8 technologies: FastAPI, datasets, OpenAI, sentencepiece, transformers, safetensors, tiktoken, and torch. Both are written in Python.

- [mlc-ai/mlc-llm](https://seerepo.com/r/mlc-ai/mlc-llm): Universal LLM Deployment Engine with ML Compilation
- [vllm-project/vllm](https://seerepo.com/r/vllm-project/vllm): A high-throughput and memory-efficient inference and serving engine for LLMs

## What they share and what sets them apart

- In common: FastAPI, datasets, OpenAI, sentencepiece, transformers, safetensors, tiktoken, torch
- Only in mlc-llm: Jetpack Compose, androidx.core:core-ktx, androidx.navigation:navigation-compose, uvicorn, lifecycle-runtime-ktx, appcompat, com.google.android.material:material, ui-graphics, MarkdownUI, prompt-toolkit, androidx.compose.material:material-icons-extended, apache-tvm-ffi, flashinfer-python
- Only in vllm: axum, gitdb, pyzmq, Hugging Face, Tokio, starlette, Ray, AIOHTTP, tower, mkdocs-material, indicatif, NVIDIA, peft, quack-kernels, einops, triton, torchvision, torchaudio, MCP, tokenizers, markdown, markupsafe, pymdown-extensions, pillow, image, jinja2, Pydantic, msgspec, jsonschema, pydantic-core, opentelemetry-api, python-json-logger, tracing, prometheus-client, psutil, tracing-subscriber, OpenTelemetry, opentelemetry-sdk, prometheus-fastapi-instrumentator

## Side by side

| | mlc-llm | vllm |
|---|---|---|
| Size | 80,952 lines written, 325 code files | 2,375,117 lines written, 3,289 code files |
| Who writes it | 0.2% of its commits signed by AI. With Claude Code, Gemini CLI, and GitHub Copilot | 12.8% of its commits signed by AI. With Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, Devin, Mistral Vibe, CodeRabbit, Factory, and Qwen Code |
| Activity | Last push October 30, 2026, 1,823 commits, 23,302 stars | Last push November 4, 2026, 24,593 commits, 96,302 stars |
| Tests | 69 test files. 16.3% of its code files have a test that imports them | 2,419 test files. 60.2% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, mlc-llm or vllm?

vllm, with 2,375,117 lines written; mlc-llm has 80,952.

The proof: [vllm-project/vllm's code at commit 75f6761](https://github.com/vllm-project/vllm/tree/75f67614971a44050140e3422c1a65fe5004a72b)

### Which has more GitHub stars, mlc-llm or vllm?

vllm, with 96,302 stars; mlc-llm has 23,302.

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

### Which has more tests, mlc-llm or vllm?

vllm, with 2,419 test files; mlc-llm has 69.

The proof: [vllm-project/vllm's code at commit 75f6761](https://github.com/vllm-project/vllm/tree/75f67614971a44050140e3422c1a65fe5004a72b)

### Which was updated more recently, mlc-llm or vllm?

vllm: its last push was on November 4, 2026, and mlc-llm's on October 30, 2026.

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

### Which has more commits signed by AI, mlc-llm or vllm?

vllm: an AI signed 12.8% of its commits, with Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, Devin, Mistral Vibe, CodeRabbit, Factory, and Qwen Code; in mlc-llm, 0.2%.

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

## Sources

- mlc-ai/mlc-llm: Read on November 4, 2026, at commit 44fd06d (https://github.com/mlc-ai/mlc-llm/tree/44fd06d04f22c87820e205b0f2b2e5e6a1f6ca85)
- vllm-project/vllm: Read on November 4, 2026, at commit 75f6761 (https://github.com/vllm-project/vllm/tree/75f67614971a44050140e3422c1a65fe5004a72b)

## 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.