Source: https://seerepo.com/compare/NVIDIA/TensorRT-LLM/vs/onyx-dot-app/onyx
Markdown source: https://seerepo.com/compare/NVIDIA/TensorRT-LLM/vs/onyx-dot-app/onyx.md
Description: TensorRT-LLM and onyx share 27 technologies: FastAPI, pyzmq, OpenAI, anyio, uvicorn, starlette, Rich, matplotlib, accelerate, NVIDIA, tiktoken, torch, triton, transformers, einops, safetensors, MCP, pillow, jinja2, mako, Pydantic, jsonschema, psutil, prometheus-client, boto3, OpenTelemetry, and prometheus-fastapi-instrumentator. Both are written in Python.

# TensorRT-LLM vs onyx

TensorRT-LLM and onyx share 27 technologies: FastAPI, pyzmq, OpenAI, anyio, uvicorn, starlette, Rich, matplotlib, accelerate, NVIDIA, tiktoken, torch, triton, transformers, einops, safetensors, MCP, pillow, jinja2, mako, Pydantic, jsonschema, psutil, prometheus-client, boto3, OpenTelemetry, and prometheus-fastapi-instrumentator. Both are written in Python.

- [NVIDIA/TensorRT-LLM](https://seerepo.com/r/NVIDIA/TensorRT-LLM): TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
- [onyx-dot-app/onyx](https://seerepo.com/r/onyx-dot-app/onyx): Open Source AI Platform - AI Chat with advanced features that works with every LLM

## What they share and what sets them apart

- In common: FastAPI, pyzmq, OpenAI, anyio, uvicorn, starlette, Rich, matplotlib, accelerate, NVIDIA, tiktoken, torch, triton, transformers, einops, safetensors, MCP, pillow, jinja2, mako, Pydantic, jsonschema, psutil, prometheus-client, boto3, OpenTelemetry, prometheus-fastapi-instrumentator
- Only in TensorRT-LLM: blobfile, h5py, Plotly, apache-tvm-ffi, cuda-python, flash-linear-attention, flashinfer-python, nvidia-cudnn-frontend, openai-codex, openai-harmony, optimum, quack-kernels, rouge, rouge-score, sentencepiece, torch-c-dlpack-ext, torchao, diffusers, torchvision, datasets, flash-attn, xgrammar, librosa, mistral-common, partial-json-parser, tritonclient, evaluate, llguidance, lm-eval, peft, jsonlines, msgspec, opentelemetry-api, opentelemetry-semantic-conventions-ai, opentelemetry-sdk
- Only in onyx: amqp, asyncpg, azure-storage-blob, azure-storage-file-datalake, fastavro, google-cloud-core, ldap3, partd, psycopg2-binary, py-key-value-aio, s3transfer, Celery, Redis, Postgres, kombu, pyairtable, Sentry, Google, Google Cloud Storage, Hugging Face, PostHog, Stripe, asgiref, fastmcp-slim, Flask, graphql-core, jupyter-core, tornado, werkzeug, AIOHTTP, fastmcp, Tauri, objc2-app-kit, objc2-foundation, Tokio, React, react-native, Expo, expo-secure-store, react-native-mmkv, Next.js, Lit, cycler, fonttools, soupsieve, charm.land/lipgloss/v2, contourpy, matplotlib-inline, prompt-toolkit, urwid, charm.land/bubbletea/v2, charm.land/bubbles/v2, SQLAlchemy, alembic, argon2-cffi, argon2-cffi-bindings, authlib, azure-identity, google-auth-httplib2, itsdangerous, joserfc, keyring, msal-extensions, pwdlib, pyjwt, python3-saml, cryptography, httpx-oauth, msal, oauthlib, requests-oauthlib, bcrypt, google-auth-oauthlib, agent-client-protocol, azure-cognitiveservices-speech, langchain-protocol, langsmith, nvidia-cudnn-cu12, onnxruntime, openinference-instrumentation, openinference-semantic-conventions, scikit-learn, litellm, chonkie, sentence-transformers, langfuse, cohere, exa-py, LangChain, tokenizers, unstructured-client, voyageai, defusedxml, docutils, et-xmlfile, lxml, lxml-html-clean, magika, mammoth, markdown-it-py, markdownify, markupsafe, mdurl, msoffcrypto-tool, olefile, pdfminer-six, pdfplumber, python-docx, python-pptx, rich-rst, ruamel-yaml, xlrd, xlsxwriter, beautifulsoup4, puremagic, github.com/yuin/goldmark, pypdf, markitdown, mistune, openpyxl, pypdfium2, reportlab, sendgrid, annotated-types, beartype, jsonschema-path, jsonschema-specifications, openapi-pydantic, referencing, pydantic-core, email-validator, azure-core, coloredlogs, execnet, opentelemetry-exporter-http-transport, opentelemetry-exporter-otlp-common, opentelemetry-semantic-conventions, python-json-logger, supervisor, botocore, github.com/sirupsen/logrus, kubernetes, aiobotocore, docker, gtk, window-vibrancy, tauri-plugin-window-state, Tailwind CSS, nativewind, class-variance-authority, tailwind-merge, react-native-svg, react-native-safe-area-context, rn-primitives, expo-image, React Hook Form, react-native-reanimated, react-native-gesture-handler, react-native-keyboard-controller, expo-splash-screen, expo-status-bar, react-native-enriched-markdown, Shopify, expo-document-picker, expo-image-picker, react-native-streamdown, next-themes, Formik, Radix UI, motion, react-dropzone, dnd-kit, lowlight, recharts, react-icons, Lucide, react-markdown, remark-gfm, highlight.js, rehype-katex, remark-math, katex, rehype-highlight, unified, docx-preview, dompurify, pdfjs-dist, react-pdf, rehype-sanitize, rehype-stringify, remark, remark-parse, xlsx, yup, TanStack, @floating-ui/react-dom, react-day-picker, marked

## Side by side

| | TensorRT-LLM | onyx |
|---|---|---|
| Size | 2,884,778 lines written, 3,120 code files | 1,626,990 lines written, 3,906 code files |
| Who writes it | 1.7% of its commits signed by AI. With Claude Code, CodeRabbit, GitHub Copilot, and Cursor | 11.7% of its commits signed by AI. With Claude Code, Devin, Cursor, CodeRabbit, GitHub Copilot, and Sweep |
| Activity | Last push November 8, 2026, 10,997 commits, 15,038 stars | Last push November 7, 2026, 11,391 commits, 33,270 stars |
| Tests | 2,703 test files. 58.6% of its code files have a test that imports them | 3,158 test files. 45.7% 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, TensorRT-LLM or onyx?

TensorRT-LLM, with 2,884,778 lines written; onyx has 1,626,990.

The proof: [NVIDIA/TensorRT-LLM's code at commit b433473](https://github.com/NVIDIA/TensorRT-LLM/tree/b433473ba0d0d49764f4d2fb3d45c82716b946dc)

### Which has more GitHub stars, TensorRT-LLM or onyx?

onyx, with 33,270 stars; TensorRT-LLM has 15,038.

The proof: [onyx-dot-app/onyx on GitHub](https://github.com/onyx-dot-app/onyx)

### Which has more tests, TensorRT-LLM or onyx?

onyx, with 3,158 test files; TensorRT-LLM has 2,703.

The proof: [onyx-dot-app/onyx's code at commit a757433](https://github.com/onyx-dot-app/onyx/tree/a757433ddef3b75a4286e026ee943c6bc63950bc)

### Which was updated more recently, TensorRT-LLM or onyx?

TensorRT-LLM: its last push was on November 8, 2026, and onyx's on November 7, 2026.

The proof: [NVIDIA/TensorRT-LLM's commits on GitHub](https://github.com/NVIDIA/TensorRT-LLM/commits)

### Which has more commits signed by AI, TensorRT-LLM or onyx?

onyx: an AI signed 11.7% of its commits, with Claude Code, Devin, Cursor, CodeRabbit, GitHub Copilot, and Sweep; in TensorRT-LLM, 1.7%.

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

## Sources

- NVIDIA/TensorRT-LLM: Read on November 8, 2026, at commit b433473 (https://github.com/NVIDIA/TensorRT-LLM/tree/b433473ba0d0d49764f4d2fb3d45c82716b946dc)
- onyx-dot-app/onyx: Read on November 7, 2026, at commit a757433 (https://github.com/onyx-dot-app/onyx/tree/a757433ddef3b75a4286e026ee943c6bc63950bc)

## 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.