Source: https://seerepo.com/compare/ai-dynamo/dynamo/vs/sgl-project/sglang
Markdown source: https://seerepo.com/compare/ai-dynamo/dynamo/vs/sgl-project/sglang.md
Description: dynamo and sglang share 34 technologies: FastAPI, axum, Redis, pyzmq, Tokio, tower, AIOHTTP, uvicorn, indicatif, dynamo-protocols, dynamo-tokenizers, dynamo-parsers, transformers, dynamo-renderer, tokenizers, hf-hub, llm-tokenizer, dynamo-multimodal, pillow, image, minijinja, Pydantic, validator, msgspec, tracing, tracing-subscriber, prometheus-client, kube, k8s-openapi, tracing-opentelemetry, OpenTelemetry, opentelemetry-otlp, psutil, and tracing-appender. dynamo is written in Rust and sglang in Python.

# dynamo vs sglang

dynamo and sglang share 34 technologies: FastAPI, axum, Redis, pyzmq, Tokio, tower, AIOHTTP, uvicorn, indicatif, dynamo-protocols, dynamo-tokenizers, dynamo-parsers, transformers, dynamo-renderer, tokenizers, hf-hub, llm-tokenizer, dynamo-multimodal, pillow, image, minijinja, Pydantic, validator, msgspec, tracing, tracing-subscriber, prometheus-client, kube, k8s-openapi, tracing-opentelemetry, OpenTelemetry, opentelemetry-otlp, psutil, and tracing-appender. dynamo is written in Rust and sglang in Python.

- [ai-dynamo/dynamo](https://seerepo.com/r/ai-dynamo/dynamo): A Datacenter Scale Distributed Inference Serving Framework
- [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, axum, Redis, pyzmq, Tokio, tower, AIOHTTP, uvicorn, indicatif, dynamo-protocols, dynamo-tokenizers, dynamo-parsers, transformers, dynamo-renderer, tokenizers, hf-hub, llm-tokenizer, dynamo-multimodal, pillow, image, minijinja, Pydantic, validator, msgspec, tracing, tracing-subscriber, prometheus-client, kube, k8s-openapi, tracing-opentelemetry, OpenTelemetry, opentelemetry-otlp, psutil, tracing-appender
- Only in dynamo: aws-sdk-s3, async-nats, aws-sdk-dynamodb, lru, object_store, opendal, moka, Jupyter, tornado, sigs.k8s.io/controller-runtime, soupsieve, plotext, seaborn, matplotlib, Plotly, dialoguer, utoipa-swagger-ui, cryptography, pyjwt, hmac, diffusers, lmcache, mooncake-transfer-engine-cuda13, nltk, cudarc, vLLM, sigs.k8s.io/gateway-api-inference-extension, tritonclient, nixl, llm-multimodal, pmdarima, prophet, scikit-learn, defusedxml, mistune, jinja2, ffmpeg-next, imageio, zip, github.com/santhosh-tekuri/jsonschema/v6, github.com/go-logr/logr, kubernetes, Prometheus, console-subscriber, k8s.io/klog/v2, kubernetes-asyncio, log, opentelemetry-appender-tracing
- Only in sglang: axum-server, data-connector, blobfile, OpenAI, Anthropic, wasmtime, tml-renderers, jsonwebtoken, smg-auth, apache-tvm-ffi, cuda-python, flashinfer-python, humming-kernels, NVIDIA, nvshmem4py-cu13, openai-harmony, openai-protocol, quack-kernels, sgl-deep-ep, sgl-deep-gemm, sgl-flash-mla, sglang-kernel, torch-c-dlpack-ext, torch, einops, torchvision, smg-mcp, compressed-tensors, gguf, smg-grpc-client, xgrammar, ModelScope, tch, tool-parser, torchaudio, reasoning-parser, deepseek-recipe, partial-json-parser, DeepSeek, mistral-common, tiktoken, decord2, kernels, llguidance, outlines, rmcp, sentencepiece, smg-grpc-servicer, timm, av, torchcodec, metrics, metrics-exporter-prometheus, openmetrics-parser, tracing-log

## Side by side

| | dynamo | sglang |
|---|---|---|
| Size | 1,919,953 lines written, 2,449 code files | 3,493,084 lines written, 4,799 code files |
| Who writes it | 12.8% of its commits signed by AI. With Claude Code, Cursor, CodeRabbit, Devin, GitHub Copilot, and Codex | 9.2% of its commits signed by AI. With Claude Code, Gemini CLI, Cursor, GitHub Copilot, Devin, Codex, CodeRabbit, and OpenHands |
| Activity | Last push November 16, 2026, 8,663 commits, 8,505 stars | Last push November 14, 2026, 22,455 commits, 38,844 stars |
| Tests | 1,550 test files. 49.1% of its code files have a test that imports them | 4,446 test files. 60.5% 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, dynamo or sglang?

sglang, with 3,493,084 lines written; dynamo has 1,919,953.

The proof: [sgl-project/sglang's code at commit bd47834](https://github.com/sgl-project/sglang/tree/bd4783409967b186ecb95956a6ab11256ce6d296)

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

sglang, with 38,844 stars; dynamo has 8,505.

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

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

sglang, with 4,446 test files; dynamo has 1,550.

The proof: [sgl-project/sglang's code at commit bd47834](https://github.com/sgl-project/sglang/tree/bd4783409967b186ecb95956a6ab11256ce6d296)

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

dynamo: its last push was on November 16, 2026, and sglang's on November 14, 2026.

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

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

dynamo: an AI signed 12.8% of its commits, with Claude Code, Cursor, CodeRabbit, Devin, GitHub Copilot, and Codex; in sglang, 9.2%.

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

## Sources

- ai-dynamo/dynamo: Read on November 17, 2026, at commit c6906b1 (https://github.com/ai-dynamo/dynamo/tree/c6906b12d078e4f8ce8dfb482101d52f92a8697f)
- sgl-project/sglang: Read on November 14, 2026, at commit bd47834 (https://github.com/sgl-project/sglang/tree/bd4783409967b186ecb95956a6ab11256ce6d296)

## 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.
