Source: https://seerepo.com/compare/EricLBuehler/mistral.rs/vs/vllm-project/vllm
Markdown source: https://seerepo.com/compare/EricLBuehler/mistral.rs/vs/vllm-project/vllm.md
Description: mistral.rs and vllm share 13 technologies: axum, Tokio, indicatif, openai-harmony, tokenizers, llguidance, safetensors, hf-hub, image, minijinja, minijinja-contrib, tracing, and tracing-subscriber. mistral.rs is written in Rust and vllm in Python.

# mistral.rs vs vllm

mistral.rs and vllm share 13 technologies: axum, Tokio, indicatif, openai-harmony, tokenizers, llguidance, safetensors, hf-hub, image, minijinja, minijinja-contrib, tracing, and tracing-subscriber. mistral.rs is written in Rust and vllm in Python.

- [EricLBuehler/mistral.rs](https://seerepo.com/r/EricLBuehler/mistral.rs): Fast, flexible LLM inference
- [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: axum, Tokio, indicatif, openai-harmony, tokenizers, llguidance, safetensors, hf-hub, image, minijinja, minijinja-contrib, tracing, tracing-subscriber
- Only in mistral.rs: objc2-foundation, Svelte, Vite, objc2-metal, comfy-table, crossterm, utoipa-swagger-ui, accelerate-src, intel-mkl-src, candle-core, candle-nn, candle-metal-kernels, cutile, bm25, csv, hound, html2text, scraper, symphonia, zip, schemars, metrics, metrics-exporter-prometheus, Tailwind CSS, Lucide, highlight.js, marked, marked-highlight, marked-katex-extension
- Only in vllm: FastAPI, gitdb, pyzmq, Hugging Face, starlette, Ray, AIOHTTP, tower, mkdocs-material, 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, oss-harmony, quack-kernels, sentencepiece, vllm-bench, vllm-chat, vllm-engine-core-client, vllm-llm, vllm-managed-engine, vllm-parser, vllm-proto, vllm-server, vllm-text, vllm-tokenizer, torch, transformers, xgrammar-structural-tag, einops, llm-multimodal, compressed-tensors, triton, mistral-common, xgrammar, partial-json-parser, torchvision, lmcache, torchaudio, timm, vllm-xpu-kernels, runai-model-streamer, tokenspeed-mla, MCP, outlines-core, tpu-inference, fastokens, fastsafetensors, instanttensor, nixl, riptoken, tekken, tensorizer, tiktoken, tiktoken-rs, markdown, markupsafe, mkdocs-material-extensions, parquet, properdocs, pymdown-extensions, selectolax, xlsxwriter, pillow, jinja2, torchcodec, annotated-types, Pydantic, msgspec, validator, opentelemetry-semantic-conventions-ai, python-json-logger, vllm-metrics, vllm-tracing, prometheus-client, psutil, tracing-futures, model-hosting-container-standards, OpenTelemetry, prometheus-fastapi-instrumentator, tracing-log

## Side by side

| | mistral.rs | vllm |
|---|---|---|
| Size | 634,906 lines written, 850 code files | 2,606,460 lines written, 3,630 code files |
| Who writes it | 0.2% of its commits signed by AI. With Claude Code 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 9, 2026, 3,249 commits, 7,848 stars | Last push November 17, 2026, 25,558 commits, 97,060 stars |
| Tests | 68 test files. 9.5% 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, mistral.rs or vllm?

vllm, with 2,606,460 lines written; mistral.rs has 634,906.

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

### Which has more GitHub stars, mistral.rs or vllm?

vllm, with 97,060 stars; mistral.rs has 7,848.

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

### Which has more tests, mistral.rs or vllm?

vllm, with 2,586 test files; mistral.rs has 68.

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

### Which was updated more recently, mistral.rs or vllm?

vllm: its last push was on November 17, 2026, and mistral.rs's on November 9, 2026.

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

### Which has more commits signed by AI, mistral.rs 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 mistral.rs, 0.2%.

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

## Sources

- EricLBuehler/mistral.rs: Read on November 18, 2026, at commit fb4cdc3 (https://github.com/EricLBuehler/mistral.rs/tree/fb4cdc3730dc64b366724e7637a205a8b7747499)
- 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.
