Source: https://seerepo.com/r/xorbitsai/inference/built Markdown source: https://seerepo.com/r/xorbitsai/inference/built.md Description: inference is a Python repo built with FastAPI, Lightning, uvicorn, AIOHTTP, anyio, and 2 more. It signs people in with python-jose and bcrypt. # What is inference built with? inference is a Python repo built with FastAPI, Lightning, uvicorn, AIOHTTP, anyio, and 2 more. It signs people in with python-jose and bcrypt, uses AI through descript-audiotools, en-core-web-sm, misaki, opencv-contrib-python-headless, pynini, and 41 more, makes its content with eva-decord, imageio-ffmpeg, pillow, torchcodec, highlight.js, and 7 more, validates its data with Pydantic and jsonschema, is tested with jsdom, deploys with opentelemetry-instrumentation-httpx, loguru, psutil, boto3, OpenTelemetry, and 2 more, and uses pyarrow and Hugging Face. It has 922,374 written lines, with 676 test files. Read on November 14, 2026, at commit d2607af. Repository: https://github.com/xorbitsai/inference ## Frontend (/) ### Interface - **[matplotlib](https://seerepo.com/uses/matplotlib)**: 22 files ## Backend (/) ### The base - **[FastAPI](https://seerepo.com/uses/fastapi)**: 31 files ### Data - **[pyarrow](https://seerepo.com/uses/pyarrow)**: 2 files ### Sign-in - **python-jose**: 2 files - **[bcrypt](https://seerepo.com/uses/bcrypt)**: 1 file ### AI - **descript-audiotools** - **en-core-web-sm** - **misaki** - **opencv-contrib-python-headless** - **pynini** - **transformers-stream-generator** - **wetextprocessing** - **[torch](https://seerepo.com/uses/torch)**: 1,215 files - **[transformers](https://seerepo.com/uses/transformers)**: 208 files - **[torchaudio](https://seerepo.com/uses/torchaudio)**: 79 files - **[einops](https://seerepo.com/uses/einops)**: 64 files - **[torchvision](https://seerepo.com/uses/torchvision)**: 42 files - **[librosa](https://seerepo.com/uses/librosa)**: 35 files - **[safetensors](https://seerepo.com/uses/safetensors)**: 25 files - **[diffusers](https://seerepo.com/uses/diffusers)**: 22 files - **[ModelScope](https://seerepo.com/uses/modelscope)**: 21 files - **[timm](https://seerepo.com/uses/timm)**: 17 files - **[onnxruntime](https://seerepo.com/uses/onnxruntime)**: 13 files - **x-transformers**: 11 files - **[accelerate](https://seerepo.com/uses/accelerate)**: 7 files - **qwen-vl-utils**: 7 files - **[tiktoken](https://seerepo.com/uses/tiktoken)**: 7 files - **funasr**: 5 files - **julius**: 4 files - **[bitsandbytes](https://seerepo.com/uses/bitsandbytes)**: 3 files - **loralib**: 3 files - **[peft](https://seerepo.com/uses/peft)**: 3 files - **pyworld**: 3 files - **[sentence-transformers](https://seerepo.com/uses/sentence-transformers)**: 3 files - **flagembedding**: 2 files - **gruut**: 2 files - **kokoro**: 2 files - **[sentencepiece](https://seerepo.com/uses/sentencepiece)**: 2 files - **silero-vad**: 2 files - **torchdiffeq**: 2 files - **vector-quantize-pytorch**: 2 files - **vocos**: 2 files - **conformer**: 1 file - **controlnet-aux**: 1 file - **fugashi**: 1 file - **g2p-en**: 1 file - **gguf**: 1 file - **[langdetect](https://seerepo.com/uses/langdetect)**: 1 file - **[optimum](https://seerepo.com/uses/optimum)**: 1 file - **tensorizer**: 1 file ### Services - **[Hugging Face](https://seerepo.com/uses/hugging-face)**: 51 files · [xinference/model/utils.py, line 48](https://github.com/xorbitsai/inference/blob/d2607afa6e252c8e69ee785e5be5d33216745186/xinference/model/utils.py#L48) - **[OpenAI](https://seerepo.com/uses/openai)**: 1 file · [xinference/_compat.py, line 57](https://github.com/xorbitsai/inference/blob/d2607afa6e252c8e69ee785e5be5d33216745186/xinference/_compat.py#L57) ## Support (/) ### The base - **[Lightning](https://seerepo.com/uses/lightning)**: 17 files - **[uvicorn](https://seerepo.com/uses/uvicorn)**: 9 files - **[AIOHTTP](https://seerepo.com/uses/aiohttp)**: 6 files - **[anyio](https://seerepo.com/uses/anyio)**: 2 files ### Content - **eva-decord** - **[imageio-ffmpeg](https://seerepo.com/uses/imageio-ffmpeg)** - **[pillow](https://seerepo.com/uses/pillow)**: 120 files - **[torchcodec](https://seerepo.com/uses/torchcodec)**: 1 file ### Validation - **[Pydantic](https://seerepo.com/uses/pydantic)**: 12 files - **[jsonschema](https://seerepo.com/uses/jsonschema)**: 1 file ### Deploy - **opentelemetry-instrumentation-httpx** - **[loguru](https://seerepo.com/uses/loguru)**: 120 files - **[psutil](https://seerepo.com/uses/psutil)**: 15 files - **[boto3](https://seerepo.com/uses/boto3)**: 1 file - **[OpenTelemetry](https://seerepo.com/uses/opentelemetry)**: 1 file - **[opentelemetry-exporter-otlp-proto-grpc](https://seerepo.com/uses/opentelemetry-exporter-otlp-proto-grpc)**: 1 file - **opentelemetry-instrumentation-fastapi**: 1 file ### Tools - **datamodel-code-generator** - **jupyterlab** - **tensorboard** - **click**: 29 files - **typing-extensions**: 8 files - **argbind**: 5 files - **Numba**: 3 files - **uv**: 1 file ### Other - **",** - **and** - **nvidia-ml-py** - **preshed** - **protobuf** - **python-multipart** - **s** - **unidic-lite** - **NumPy**: 437 files - **tqdm**: 80 files - **soundfile**: 50 files - **omegaconf**: 34 files - **requests**: 19 files - **tabulate**: 11 files - **pydub**: 10 files - **cached-path**: 6 files - **inflect**: 6 files - **jieba**: 5 files - **ormsgpack**: 5 files - **json5**: 4 files - **pypinyin**: 4 files - **xxhash**: 4 files - **hydra-core**: 3 files - **hyperpyyaml**: 3 files - **natsort**: 3 files - **pyloudnorm**: 3 files - **setproctitle**: 3 files - **sse-starlette**: 3 files - **tomli**: 3 files - **cn2an**: 2 files - **ffmpy**: 2 files - **flatten-dict**: 2 files - **munch**: 2 files - **num2words**: 2 files - **pykakasi**: 2 files - **anyascii**: 1 file - **async-timeout**: 1 file - **cachetools**: 1 file - **gdown**: 1 file - **orjson**: 1 file - **pandas**: 1 file - **randomname**: 1 file ## Frontend (frontend) ### The base - **[React](https://seerepo.com/uses/react)**: 135 files · [in frontend/package.json](https://github.com/xorbitsai/inference/blob/d2607afa6e252c8e69ee785e5be5d33216745186/frontend/package.json) - **[Next.js](https://seerepo.com/uses/nextjs)**: 25 files · [in frontend/package.json](https://github.com/xorbitsai/inference/blob/d2607afa6e252c8e69ee785e5be5d33216745186/frontend/package.json) ### Styles - **[Tailwind CSS](https://seerepo.com/uses/tailwind-css)** - **[next-themes](https://seerepo.com/uses/next-themes)**: 5 files - **[class-variance-authority](https://seerepo.com/uses/class-variance-authority)**: 4 files - **[tailwind-merge](https://seerepo.com/uses/tailwind-merge)**: 1 file ### Interface - **[sonner](https://seerepo.com/uses/sonner)**: 30 files - **[Radix UI](https://seerepo.com/uses/radix-ui)**: 20 files ### Icons - **[Lucide](https://seerepo.com/uses/lucide)**: 92 files - **[react-icons](https://seerepo.com/uses/react-icons)**: 1 file ## Support (frontend) ### Content - **[highlight.js](https://seerepo.com/uses/highlightjs)**: 1 file - **[Nunjucks](https://seerepo.com/uses/nunjucks)**: 1 file - **[react-markdown](https://seerepo.com/uses/react-markdown)**: 1 file - **[rehype-katex](https://seerepo.com/uses/rehype-katex)**: 1 file - **[rehype-raw](https://seerepo.com/uses/rehype-raw)**: 1 file - **[rehype-sanitize](https://seerepo.com/uses/rehype-sanitize)**: 1 file - **[remark-gfm](https://seerepo.com/uses/remark-gfm)**: 1 file - **[remark-math](https://seerepo.com/uses/remark-math)**: 1 file ### Testing - **jsdom**: 26 files ### Tools - **TypeScript**: 4 files ### Other - **Axios**: 10 files - **date-fns**: 5 files - **clsx**: 1 file ## Other repos with a similar stack - [mudler/LocalAI](https://seerepo.com/r/mudler/LocalAI/built): FastAPI, pyarrow, Hugging Face, OpenAI, Lightning, uvicorn, anyio, React, matplotlib, torch, transformers, torchaudio, einops, torchvision, librosa, safetensors, diffusers, ModelScope, onnxruntime, accelerate, tiktoken, funasr, bitsandbytes, peft, sentence-transformers, kokoro, sentencepiece, vector-quantize-pytorch, conformer, optimum, imageio-ffmpeg, pillow, torchcodec, loguru, OpenTelemetry, highlight.js · [Compare](https://seerepo.com/compare/mudler/LocalAI/vs/xorbitsai/inference) - [bojieli/ai-agent-book](https://seerepo.com/r/bojieli/ai-agent-book/built): FastAPI, pyarrow, Hugging Face, OpenAI, uvicorn, AIOHTTP, anyio, React, Next.js, matplotlib, torch, transformers, torchaudio, librosa, accelerate, tiktoken, bitsandbytes, peft, sentence-transformers, flagembedding, sentencepiece, pillow, torchcodec, Pydantic, loguru, psutil, Tailwind CSS, class-variance-authority, tailwind-merge, Radix UI, Lucide, react-markdown, remark-gfm · [Compare](https://seerepo.com/compare/bojieli/ai-agent-book/vs/xorbitsai/inference) - [unslothai/unsloth](https://seerepo.com/r/unslothai/unsloth/built): FastAPI, Hugging Face, OpenAI, uvicorn, anyio, React, matplotlib, descript-audiotools, torch, transformers, einops, librosa, safetensors, diffusers, timm, accelerate, tiktoken, julius, peft, sentence-transformers, sentencepiece, gguf, pillow, Pydantic, loguru, psutil, Tailwind CSS, class-variance-authority, tailwind-merge, sonner, Radix UI, Lucide · [Compare](https://seerepo.com/compare/unslothai/unsloth/vs/xorbitsai/inference) - [debpalash/VoiceStudio](https://seerepo.com/r/debpalash/VoiceStudio/built): FastAPI, pyarrow, Hugging Face, OpenAI, Lightning, uvicorn, React, matplotlib, bcrypt, torch, transformers, torchaudio, torchvision, librosa, diffusers, ModelScope, onnxruntime, x-transformers, accelerate, conformer, pillow, Pydantic, loguru, psutil, boto3, Tailwind CSS, class-variance-authority, tailwind-merge, sonner, Radix UI, Lucide · [Compare](https://seerepo.com/compare/debpalash/VoiceStudio/vs/xorbitsai/inference) - [ray-project/ray](https://seerepo.com/r/ray-project/ray/built): FastAPI, pyarrow, Hugging Face, Lightning, uvicorn, AIOHTTP, anyio, React, torch, transformers, einops, torchvision, safetensors, diffusers, timm, onnxruntime, tiktoken, bitsandbytes, peft, sentencepiece, imageio-ffmpeg, pillow, torchcodec, Pydantic, jsonschema, psutil, boto3, OpenTelemetry, opentelemetry-exporter-otlp-proto-grpc, opentelemetry-instrumentation-fastapi, react-icons · [Compare](https://seerepo.com/compare/ray-project/ray/vs/xorbitsai/inference) - [datawhalechina/hello-agents](https://seerepo.com/r/datawhalechina/hello-agents/built): FastAPI, Hugging Face, OpenAI, uvicorn, AIOHTTP, anyio, React, matplotlib, python-jose, bcrypt, torch, transformers, safetensors, onnxruntime, accelerate, tiktoken, bitsandbytes, peft, sentence-transformers, langdetect, pillow, Pydantic, jsonschema, loguru, OpenTelemetry, opentelemetry-exporter-otlp-proto-grpc, Tailwind CSS, highlight.js, react-markdown · [Compare](https://seerepo.com/compare/datawhalechina/hello-agents/vs/xorbitsai/inference) ## Frequently asked questions ### What language is inference written in? inference is written in Python, with 922,374 written lines. ### What framework does inference use? inference is built with FastAPI, Lightning, uvicorn, AIOHTTP, anyio, React, and Next.js. ### What does inference sign people in with? inference signs people in with python-jose and bcrypt. ### Does inference use AI? Yes. inference uses AI through descript-audiotools, en-core-web-sm, misaki, opencv-contrib-python-headless, pynini, transformers-stream-generator, wetextprocessing, torch, transformers, torchaudio, einops, torchvision, librosa, safetensors, diffusers, ModelScope, timm, onnxruntime, x-transformers, accelerate, qwen-vl-utils, tiktoken, funasr, julius, bitsandbytes, loralib, peft, pyworld, sentence-transformers, flagembedding, gruut, kokoro, sentencepiece, silero-vad, torchdiffeq, vector-quantize-pytorch, vocos, conformer, controlnet-aux, fugashi, g2p-en, gguf, langdetect, optimum, tensorizer, and OpenAI. ### What services does inference use? inference uses pyarrow and Hugging Face. ### Does inference have tests? Yes. inference has 676 test files and is tested with jsdom. ### Which repos have a stack like inference's? The ones that share most of its stack: mudler/LocalAI, bojieli/ai-agent-book, and unslothai/unsloth. ## 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.