Source: https://seerepo.com/compare/ml-explore/mlx-lm/vs/vllm-project/vllm
Markdown source: https://seerepo.com/compare/ml-explore/mlx-lm/vs/vllm-project/vllm.md
Description: mlx-lm and vllm share 4 technologies: sentencepiece, transformers, jinja2, and pillow. Both are written in Python.

# mlx-lm vs vllm

mlx-lm and vllm share 4 technologies: sentencepiece, transformers, jinja2, and pillow. Both are written in Python.

- [ml-explore/mlx-lm](https://seerepo.com/r/ml-explore/mlx-lm): Run LLMs with MLX
- [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: sentencepiece, transformers, jinja2, pillow
- Only in mlx-lm: mlx
- Only in vllm: FastAPI, axum, gitdb, pyzmq, Hugging Face, Tokio, starlette, Ray, AIOHTTP, tower, mkdocs-material, indicatif, AMD, apache-tvm-ffi, auto-round-lib, conch-triton-kernels, cuda-bindings, cuda-python, cupy-cuda12x, cupy-cuda13x, flashinfer-python, humming-kernels, lm-format-enforcer, mooncake-transfer-engine, mooncake-transfer-engine-rocm, NVIDIA, nvidia-cudnn-frontend, OpenAI, openai-harmony, oss-harmony, quack-kernels, vllm-bench, vllm-chat, vllm-engine-core-client, vllm-llm, vllm-managed-engine, vllm-parser, vllm-proto, vllm-server, vllm-text, vllm-tokenizer, torch, xgrammar-structural-tag, einops, llm-multimodal, compressed-tensors, safetensors, triton, mistral-common, xgrammar, partial-json-parser, torchvision, lmcache, torchaudio, timm, vllm-xpu-kernels, runai-model-streamer, tokenizers, tokenspeed-mla, llguidance, MCP, outlines-core, tpu-inference, fastokens, fastsafetensors, hf-hub, instanttensor, nixl, riptoken, tekken, tensorizer, tiktoken, tiktoken-rs, markdown, markupsafe, mkdocs-material-extensions, parquet, properdocs, pymdown-extensions, selectolax, xlsxwriter, image, minijinja, torchcodec, minijinja-contrib, annotated-types, Pydantic, msgspec, validator, opentelemetry-semantic-conventions-ai, python-json-logger, vllm-metrics, vllm-tracing, tracing, prometheus-client, psutil, tracing-futures, tracing-subscriber, model-hosting-container-standards, OpenTelemetry, prometheus-fastapi-instrumentator, tracing-log

## Side by side

| | mlx-lm | vllm |
|---|---|---|
| Size | 77,344 lines written, 205 code files | 2,606,460 lines written, 3,630 code files |
| Who writes it | 0.8% of its commits signed by AI. With Claude Code, Cursor, and GitHub Copilot | 14.7% 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 November 18, 2026, 998 commits, 7,695 stars | Last push November 17, 2026, 25,558 commits, 97,060 stars |
| Tests | 28 test files. 67.3% of its code files have a test that imports them | 2,586 test files. 60.7% 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, mlx-lm or vllm?

vllm, with 2,606,460 lines written; mlx-lm has 77,344.

The proof: [vllm-project/vllm's code at commit 61c3895](https://github.com/vllm-project/vllm/tree/61c3895fc937b4ffc2a59abe188959de1e459c8a)

### Which has more GitHub stars, mlx-lm or vllm?

vllm, with 97,060 stars; mlx-lm has 7,695.

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

### Which has more tests, mlx-lm or vllm?

vllm, with 2,586 test files; mlx-lm has 28.

The proof: [vllm-project/vllm's code at commit 61c3895](https://github.com/vllm-project/vllm/tree/61c3895fc937b4ffc2a59abe188959de1e459c8a)

### Which was updated more recently, mlx-lm or vllm?

mlx-lm: its last push was on November 18, 2026, and vllm's on November 17, 2026.

The proof: [ml-explore/mlx-lm's commits on GitHub](https://github.com/ml-explore/mlx-lm/commits)

### Which has more commits signed by AI, mlx-lm or vllm?

vllm: an AI signed 14.7% of its commits, with Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, Devin, Mistral Vibe, CodeRabbit, Factory, and Qwen Code; in mlx-lm, 0.8%.

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

## Sources

- ml-explore/mlx-lm: Read on November 19, 2026, at commit c4c9c76 (https://github.com/ml-explore/mlx-lm/tree/c4c9c762cc797fd979fc98645f5db5112753bbe9)
- vllm-project/vllm: Read on November 17, 2026, at commit 61c3895 (https://github.com/vllm-project/vllm/tree/61c3895fc937b4ffc2a59abe188959de1e459c8a)

## 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.
