Source: https://seerepo.com/compare/InternLM/lmdeploy/vs/sgl-project/sglang
Markdown source: https://seerepo.com/compare/InternLM/lmdeploy/vs/sgl-project/sglang.md
Description: lmdeploy and sglang share 20 technologies: FastAPI, pyzmq, Anthropic, OpenAI, AIOHTTP, uvicorn, apache-tvm-ffi, openai-harmony, partial-json-parser, torch, transformers, xgrammar, torchvision, einops, sentencepiece, tiktoken, timm, pillow, Pydantic, and prometheus-client. Both are written in Python.

# lmdeploy vs sglang

lmdeploy and sglang share 20 technologies: FastAPI, pyzmq, Anthropic, OpenAI, AIOHTTP, uvicorn, apache-tvm-ffi, openai-harmony, partial-json-parser, torch, transformers, xgrammar, torchvision, einops, sentencepiece, tiktoken, timm, pillow, Pydantic, and prometheus-client. Both are written in Python.

- [InternLM/lmdeploy](https://seerepo.com/r/InternLM/lmdeploy): LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
- [sgl-project/sglang](https://seerepo.com/r/sgl-project/sglang): SGLang is a high-performance serving framework for large language models and multimodal models.

## What they share and what sets them apart

- In common: FastAPI, pyzmq, Anthropic, OpenAI, AIOHTTP, uvicorn, apache-tvm-ffi, openai-harmony, partial-json-parser, torch, transformers, xgrammar, torchvision, einops, sentencepiece, tiktoken, timm, pillow, Pydantic, prometheus-client
- Only in lmdeploy: Ray, sphinx-book-theme, matplotlib, flash-linear-attention, qwen-vl-utils, rdkit, transformers-stream-generator, triton, accelerate, safetensors, peft, torch-npu, datasets, markdown, myst-parser
- Only in sglang: axum, blobfile, Tokio, tower, indicatif, tml-renderers, cuda-python, flashinfer-python, humming-kernels, NVIDIA, nvshmem4py-cu13, quack-kernels, sgl-deep-ep, sgl-deep-gemm, sgl-flash-mla, sglang-kernel, torch-c-dlpack-ext, dynamo-renderer, dynamo-protocols, compressed-tensors, gguf, dynamo-tokenizers, tokenizers, dynamo-parsers, ModelScope, tch, torchaudio, dynamo-multimodal, deepseek-recipe, hf-hub, DeepSeek, mistral-common, sgl-fa3, decord2, kernels, llguidance, outlines, minijinja, av, torchcodec, image, msgspec, tracing, psutil, tracing-subscriber, k8s-openapi, kube, tracing-appender

## Side by side

| | lmdeploy | sglang |
|---|---|---|
| Size | 299,565 lines written, 789 code files | 3,493,138 lines written, 4,746 code files |
| Who writes it | 1.2% of its commits signed by AI. With Claude Code, GitHub Copilot, Cursor, and OpenHands | 9.5% of its commits signed by AI. With Claude Code, Gemini CLI, Cursor, GitHub Copilot, Codex, Devin, CodeRabbit, and OpenHands |
| Activity | Last push November 17, 2026, 2,189 commits, 8,149 stars | Last push November 19, 2026, 22,827 commits, 39,041 stars |
| Tests | 336 test files. 44.1% of its code files have a test that imports them | 4,429 test files. 62.5% 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, lmdeploy or sglang?

sglang, with 3,493,138 lines written; lmdeploy has 299,565.

The proof: [sgl-project/sglang's code at commit a3eae55](https://github.com/sgl-project/sglang/tree/a3eae555453777c3f4c5ab41e19ef1c9577e0785)

### Which has more GitHub stars, lmdeploy or sglang?

sglang, with 39,041 stars; lmdeploy has 8,149.

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

### Which has more tests, lmdeploy or sglang?

sglang, with 4,429 test files; lmdeploy has 336.

The proof: [sgl-project/sglang's code at commit a3eae55](https://github.com/sgl-project/sglang/tree/a3eae555453777c3f4c5ab41e19ef1c9577e0785)

### Which was updated more recently, lmdeploy or sglang?

sglang: its last push was on November 19, 2026, and lmdeploy's on November 17, 2026.

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

### Which has more commits signed by AI, lmdeploy or sglang?

sglang: an AI signed 9.5% of its commits, with Claude Code, Gemini CLI, Cursor, GitHub Copilot, Codex, Devin, CodeRabbit, and OpenHands; in lmdeploy, 1.2%.

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

## Sources

- InternLM/lmdeploy: Read on November 17, 2026, at commit fc33f69 (https://github.com/InternLM/lmdeploy/tree/fc33f69736ff48c10ad720593b021dcdaedcb80d)
- sgl-project/sglang: Read on November 19, 2026, at commit a3eae55 (https://github.com/sgl-project/sglang/tree/a3eae555453777c3f4c5ab41e19ef1c9577e0785)

## 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.
