Source: https://seerepo.com/compare/tile-ai/tilelang/vs/vllm-project/vllm
Markdown source: https://seerepo.com/compare/tile-ai/tilelang/vs/vllm-project/vllm.md
Description: tilelang and vllm share 6 technologies: apache-tvm-ffi, cuda-python, einops, NVIDIA, torch, and psutil. Both are written in Python.

# tilelang vs vllm

tilelang and vllm share 6 technologies: apache-tvm-ffi, cuda-python, einops, NVIDIA, torch, and psutil. Both are written in Python.

- [tile-ai/tilelang](https://seerepo.com/r/tile-ai/tilelang):  Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
- [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: apache-tvm-ffi, cuda-python, einops, NVIDIA, torch, psutil
- Only in tilelang: tornado, seaborn, matplotlib, flash-attn, flash-linear-attention, ml-dtypes, torch-c-dlpack-ext, docutils
- Only in vllm: FastAPI, axum, gitdb, pyzmq, Hugging Face, Tokio, starlette, Ray, AIOHTTP, tower, mkdocs-material, indicatif, AMD, auto-round-lib, conch-triton-kernels, cuda-bindings, cupy-cuda12x, cupy-cuda13x, flashinfer-python, humming-kernels, lm-format-enforcer, mooncake-transfer-engine, mooncake-transfer-engine-rocm, nvidia-cudnn-frontend, OpenAI, openai-harmony, 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, transformers, xgrammar-structural-tag, 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, pillow, image, jinja2, minijinja, torchcodec, minijinja-contrib, annotated-types, Pydantic, msgspec, validator, opentelemetry-semantic-conventions-ai, python-json-logger, vllm-metrics, vllm-tracing, tracing, prometheus-client, tracing-subscriber, tracing-futures, model-hosting-container-standards, OpenTelemetry, prometheus-fastapi-instrumentator, tracing-log

## Side by side

| | tilelang | vllm |
|---|---|---|
| Size | 324,472 lines written, 455 code files | 2,489,750 lines written, 3,450 code files |
| Who writes it | 4.5% of its commits signed by AI. With Claude Code, CodeRabbit, GitHub Copilot, Gemini CLI, Codex, and Cursor | 14% 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 13, 2026, 2,194 commits, 8,976 stars | Last push November 12, 2026, 25,200 commits, 96,790 stars |
| Tests | 633 test files. 37.6% of its code files have a test that imports them | 2,521 test files. 61.1% 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, tilelang or vllm?

vllm, with 2,489,750 lines written; tilelang has 324,472.

The proof: [vllm-project/vllm's code at commit c6573ee](https://github.com/vllm-project/vllm/tree/c6573eed5e56fd39b01d610db04616ed9b221851)

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

vllm, with 96,790 stars; tilelang has 8,976.

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

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

vllm, with 2,521 test files; tilelang has 633.

The proof: [vllm-project/vllm's code at commit c6573ee](https://github.com/vllm-project/vllm/tree/c6573eed5e56fd39b01d610db04616ed9b221851)

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

tilelang: its last push was on November 13, 2026, and vllm's on November 12, 2026.

The proof: [tile-ai/tilelang's commits on GitHub](https://github.com/tile-ai/tilelang/commits)

### Which has more commits signed by AI, tilelang or vllm?

vllm: an AI signed 14% of its commits, with Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, Devin, Mistral Vibe, CodeRabbit, Factory, and Qwen Code; in tilelang, 4.5%.

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

## Sources

- tile-ai/tilelang: Read on November 15, 2026, at commit 210611d (https://github.com/tile-ai/tilelang/tree/210611dca01198cacac9a02103c2a95e18cf6375)
- vllm-project/vllm: Read on November 12, 2026, at commit c6573ee (https://github.com/vllm-project/vllm/tree/c6573eed5e56fd39b01d610db04616ed9b221851)

## 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.
