Source: https://seerepo.com/compare/run-llama/llama_index/vs/vllm-project/vllm
Markdown source: https://seerepo.com/compare/run-llama/llama_index/vs/vllm-project/vllm.md
Description: llama_index and vllm share 25 technologies: starlette, pyzmq, AIOHTTP, Ray, einops, OpenAI, torch, transformers, tiktoken, MCP, sentencepiece, datasets, peft, tokenizers, markupsafe, pillow, jinja2, Pydantic, jsonschema, pydantic-core, opentelemetry-api, prometheus-client, psutil, python-json-logger, and OpenTelemetry. Both are written in Python.

# llama_index vs vllm

llama_index and vllm share 25 technologies: starlette, pyzmq, AIOHTTP, Ray, einops, OpenAI, torch, transformers, tiktoken, MCP, sentencepiece, datasets, peft, tokenizers, markupsafe, pillow, jinja2, Pydantic, jsonschema, pydantic-core, opentelemetry-api, prometheus-client, psutil, python-json-logger, and OpenTelemetry. Both are written in Python.

- [run-llama/llama_index](https://seerepo.com/r/run-llama/llama_index): LlamaIndex is the document processing platform for AI
- [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: starlette, pyzmq, AIOHTTP, Ray, einops, OpenAI, torch, transformers, tiktoken, MCP, sentencepiece, datasets, peft, tokenizers, markupsafe, pillow, jinja2, Pydantic, jsonschema, pydantic-core, opentelemetry-api, prometheus-client, psutil, python-json-logger, OpenTelemetry
- Only in llama_index: aiomysql, aiosqlite, async-lru, asyncpg, azure-search-documents, azure-storage-blob, ibm-db, pgvecto-rs, pgvector, psycopg, psycopg2-binary, Redis, weaviate-client, pyarrow, lancedb, oracledb, DuckDB, pymilvus, SQLite, tablestore, chromadb, falkordb, MySQL, pinecone, clickhouse-connect, gcsfs, pyiceberg, pymochow, pymysql, pyobvector, s3fs, tcvectordb, typesense, ElevenLabs, anyio, graphql-core, tornado, soupsieve, tinycss2, ipywidgets, matplotlib-inline, prompt-toolkit, matplotlib, Rich, SQLAlchemy, argon2-cffi, azure-identity, Google, google-auth-httplib2, google-auth-oauthlib, cryptography, pyjwt, msal, firecrawl-py, guardrails-ai, llama-index-core, mem0ai, opencv-python, PaddlePaddle, tavily-python, ibm-watsonx-ai, cohere, LangChain, sentence-transformers, dashscope, fastembed, flagembedding, nltk, litellm, ModelScope, Ollama, openvino, scikit-learn, tritonclient, vLLM, exa-py, flashrank, hnswlib, langfuse, mlx, mlx-lm, nomic, optimum, paddleocr, presidio-analyzer, beautifulsoup4, bleach, mistune, nbformat, newspaper3k, xlrd, bs4, html2text, unstructured, defusedxml, lxml, pymupdf, filetype, docx2txt, markdownify, docling, lxml-html-clean, markitdown, nbconvert, pdf2image, pdfplumber, pypdf, pypdf2, tinytag, youtube-transcript-api, jsonschema-specifications, marshmallow, referencing, rfc3339-validator, docling-core, annotated-types, opentelemetry-semantic-conventions, boto3, docker, Alibaba Cloud
- Only in vllm: FastAPI, axum, gitdb, Hugging Face, Tokio, tower, mkdocs-material, indicatif, NVIDIA, quack-kernels, safetensors, triton, torchvision, torchaudio, markdown, pymdown-extensions, image, msgspec, tracing, tracing-subscriber, opentelemetry-sdk, prometheus-fastapi-instrumentator

## Side by side

| | llama_index | vllm |
|---|---|---|
| Size | 473,236 lines written, 2,055 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, Cursor, 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 November 5, 2026, 7,963 commits, 52,820 stars | Last push November 4, 2026, 24,593 commits, 96,302 stars |
| Tests | 1,607 test files. 46.5% 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, llama_index or vllm?

vllm, with 2,375,117 lines written; llama_index has 473,236.

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

### Which has more GitHub stars, llama_index or vllm?

vllm, with 96,302 stars; llama_index has 52,820.

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

### Which has more tests, llama_index or vllm?

vllm, with 2,419 test files; llama_index has 1,607.

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

### Which was updated more recently, llama_index or vllm?

llama_index: its last push was on November 5, 2026, and vllm's on November 4, 2026.

The proof: [run-llama/llama_index's commits on GitHub](https://github.com/run-llama/llama_index/commits)

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

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

## Sources

- run-llama/llama_index: Read on November 5, 2026, at commit 444fdf0 (https://github.com/run-llama/llama_index/tree/444fdf0684707de62ebb447d658dba137dd9cb99)
- 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.