awesome-llama: https://github.com/xorbitsai/inference
artificial-intelligence diffusers gemma glm glm-5-3 inference kimi kimi-k3 llama-cpp llamacpp llm machine-learning mlx openai-api pytorch qwen sglang transformers vllm whisper
Score: 22.947438354878493
Last synced: 1 day ago
JSON representation
Repository metadata:
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.
- Host: GitHub
- URL: https://github.com/xorbitsai/inference
- Owner: xorbitsai
- License: apache-2.0
- Created: 2023-06-14T07:05:04.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2026-10-21T05:20:56.000Z (6 days ago)
- Last Synced: 2026-10-21T07:16:30.497Z (6 days ago)
- Topics: artificial-intelligence, diffusers, gemma, glm, glm-5-3, inference, kimi, kimi-k3, llama-cpp, llamacpp, llm, machine-learning, mlx, openai-api, pytorch, qwen, sglang, transformers, vllm, whisper
- Language: Python
- Homepage: https://inference.readthedocs.io
- Size: 96.4 MB
- Stars: 9,620
- Watchers: 63
- Forks: 885
- Open Issues: 34
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Security: SECURITY.md
- Agents: AGENTS.md
- Claude: CLAUDE.md
Owner metadata:
- Name: Xorbits
- Login: xorbitsai
- Email:
- Kind: organization
- Description: Xorbits builds production-ready infrastructure for Model Inference and AI Agents.
- Website: xinference.co
- Location: Singapore
- Twitter: Xorbitsio
- Company:
- Icon url: https://avatars.githubusercontent.com/u/109655068?v=4
- Repositories: 19
- Last Synced at: 2026-10-24T21:49:21.267Z
- Profile URL: https://github.com/xorbitsai
GitHub Events
Total
- Commit comment event: 1
- Create event: 87
- Delete event: 61
- Fork event: 343
- Issue comment event: 5602
- Issues event: 2369
- Member event: 5
- Pull request event: 1085
- Pull request review comment event: 253
- Pull request review event: 642
- Push event: 746
- Release event: 40
- Watch event: 3390
- Total: 14624
Last Year
- Commit comment event: 1
- Create event: 49
- Delete event: 49
- Fork event: 32
- Issue comment event: 653
- Issues event: 504
- Member event: 1
- Pull request event: 383
- Pull request review comment event: 76
- Pull request review event: 174
- Push event: 399
- Release event: 8
- Watch event: 337
- Total: 2666
Committers metadata
Last synced: 2 days ago
Total Commits: 2,573
Total Committers: 184
Avg Commits per committer: 13.984
Development Distribution Score (DDS): 0.83
Commits in past year: 1,107
Committers in past year: 78
Avg Commits per committer in past year: 14.192
Development Distribution Score (DDS) in past year: 0.824
| Name | Commits | |
|---|---|---|
| Chris Qin | q****e@g****m | 438 |
| m199369309 | z****i@c****m | 173 |
| codingl2k1 | 1****1 | 171 |
| Chengjie Li | 1****8 | 167 |
| OliverBryant | 5****t | 147 |
| Uranus | 1****n | 136 |
| Minamiyama | m****a@q****m | 131 |
| amumu96 | 1****6 | 112 |
| aresnow1 | 1****1 | 96 |
| xiaolei | 1****s | 95 |
| llyycchhee | m****9@1****m | 86 |
| XprobeBot | 1****t | 73 |
| Jun-Howie | 6****e | 61 |
| 呆萌闷油瓶 | 2****2@q****m | 51 |
| Jack Liang | 1****1 | 36 |
| zwt-1234 | 1****4 | 31 |
| pangyoki | p****i@1****m | 29 |
| Bojun-Feng | 1****g | 29 |
| Dreamsome | o****k@g****m | 28 |
| Yanze (David) Wu | 1****9 | 22 |
| jiayini1119 | 1****9 | 21 |
| Adam Ning | f****t@g****m | 20 |
| hainaweiben | 1****n | 19 |
| Rui Ji | r****i@u****u | 17 |
| maoyuehui | 1****i | 15 |
| JW | k****3@g****m | 14 |
| Tai An | a****1@o****m | 13 |
| Tymur | 4****3 | 12 |
| souljoy | z****e@1****m | 12 |
| ZhikaiGuo960110 | t****o@v****m | 11 |
| and 154 more... | ||
Issue and Pull Request metadata
Last synced: 1 day ago
Total issues: 2,291
Total pull requests: 2,004
Average time to close issues: about 1 month
Average time to close pull requests: 6 days
Total issue authors: 1,168
Total pull request authors: 178
Average comments per issue: 3.1
Average comments per pull request: 0.58
Merged pull request: 1,579
Bot issues: 7
Bot pull requests: 3
Past year issues: 96
Past year pull requests: 399
Past year average time to close issues: 13 days
Past year average time to close pull requests: 3 days
Past year issue authors: 54
Past year pull request authors: 45
Past year average comments per issue: 2.42
Past year average comments per pull request: 0.73
Past year merged pull request: 328
Past year bot issues: 6
Past year bot pull requests: 0
Top Issue Authors
- UranusSeven (52)
- Minamiyama (28)
- leslie2046 (27)
- qinxuye (23)
- Songjiadong (19)
- lordk911 (18)
- aresnow1 (18)
- moshilangzi (16)
- xs818818 (14)
- yidasanqian (13)
- rexjm (12)
- amumu96 (12)
- wangyongpenga (12)
- kelliaao (12)
- frankSARU (11)
Top Pull Request Authors
- qinxuye (409)
- codingl2k1 (173)
- Minamiyama (162)
- amumu96 (144)
- ChengjieLi28 (142)
- yiboyasss (114)
- m199369309 (91)
- Jun-Howie (84)
- aresnow1 (40)
- OliverBryant (38)
- frostyplanet (32)
- llyycchhee (29)
- UranusSeven (28)
- leslie2046 (24)
- hainaweiben (24)
Top Issue Labels
- stale (985)
- gpu (768)
- feature (331)
- question (173)
- bug (99)
- enhancement (42)
- good first issue (20)
- help wanted (17)
- new model (16)
- pr welcome (12)
- documentation (6)
- testing (2)
- refactor (2)
- duplicate (2)
- build (2)
- Mend: dependency security vulnerability (1)
- high priority (1)
Top Pull Request Labels
- feature (623)
- bug (463)
- enhancement (306)
- gpu (164)
- documentation (153)
- build (61)
- refactor (47)
- testing (13)
- new model (7)
- dependencies (3)
- question (3)
- stale (2)
- api (1)
- verify (1)
- SQL (1)
- Stale (1)
- javascript (1)
- kubeapps-apprepository-controller (1)
- auto-merge (1)
- automated (1)
Package metadata
- Total packages: 2
-
Total downloads:
- pypi: 4,440 last-month
- Total docker downloads: 750
- Total dependent packages: 3 (may contain duplicates)
- Total dependent repositories: 9 (may contain duplicates)
- Total versions: 292
- Total maintainers: 1
- Total advisories: 1
pypi.org: xinference
Model Serving Made Easy
- Homepage: https://github.com/xorbitsai/inference
- Documentation: https://xinference.readthedocs.io/
- Licenses: Apache-2.0
- Latest release: 4.1.0 (published 2 days ago)
- Last Synced: 2026-10-25T09:13:06.648Z (2 days ago)
- Versions: 158
- Dependent Packages: 3
- Dependent Repositories: 9
- Downloads: 4,440 Last month
- Docker Downloads: 750
-
Rankings:
- Stargazers count: 2.027%
- Downloads: 3.469%
- Average: 4.666%
- Dependent repos count: 4.955%
- Forks count: 5.508%
- Dependent packages count: 7.373%
- Maintainers (1)
- Advisories:
proxy.golang.org: github.com/xorbitsai/inference
- Homepage:
- Documentation: https://pkg.go.dev/github.com/xorbitsai/inference#section-documentation
- Licenses: apache-2.0
- Latest release: v4.0.1+incompatible (published 9 days ago)
- Last Synced: 2026-10-25T10:01:12.146Z (2 days ago)
- Versions: 134
- Dependent Packages: 0
- Dependent Repositories: 0
-
Rankings:
- Dependent packages count: 6.528%
- Average: 6.747%
- Dependent repos count: 6.966%
Dependencies
- actions/checkout v3 composite
- actions/setup-python v4 composite
- codecov/codecov-action v3 composite
- conda-incubator/setup-miniconda v2 composite
- isort/isort-action master composite
- psf/black stable composite
- py-actions/flake8 v2 composite
- actions/checkout v3 composite
- actions/setup-python v4 composite
- pypa/gh-action-pypi-publish v1.5.0 composite
- @eslint/eslintrc ^3 development
- @svgr/webpack ^8.1.0 development
- @types/node ^20 development
- @types/nunjucks ^3.2.6 development
- @types/react ^19 development
- @types/react-dom ^19 development
- eslint ^9 development
- eslint-config-next 15.2.3 development
- eslint-config-prettier ^10.1.8 development
- prettier ^3.8.3 development
- tailwindcss ^3.4.17 development
- typescript ^5 development
- @radix-ui/react-alert-dialog ^1.1.15
- @radix-ui/react-checkbox ^1.3.3
- @radix-ui/react-collapsible ^1.1.12
- @radix-ui/react-dialog ^1.1.15
- @radix-ui/react-dropdown-menu ^2.1.15
- @radix-ui/react-icons ^1.3.0
- @radix-ui/react-label ^2.1.7
- @radix-ui/react-popover ^1.1.15
- @radix-ui/react-progress ^1.1.7
- @radix-ui/react-radio-group ^1.3.8
- @radix-ui/react-scroll-area ^1.2.10
- @radix-ui/react-select ^2.2.6
- @radix-ui/react-separator ^1.1.7
- @radix-ui/react-slider ^1.3.6
- @radix-ui/react-slot ^1.2.3
- @radix-ui/react-switch ^1.2.6
- @radix-ui/react-tabs ^1.1.13
- @radix-ui/react-tooltip ^1.2.8
- @tailwindcss/typography ^0.5.19
- autoprefixer ^10.4.0
- axios ^1.16.0
- class-variance-authority ^0.7.1
- clsx ^2.1.1
- date-fns ^4.1.0
- highlight.js ^11.11.1
- lucide-react ^1.16.0
- marked ^5.1.2
- next 15.2.3
- next-themes ^0.4.6
- nunjucks ^3.2.4
- react ^19.0.0
- react-dom ^19.0.0
- react-icons ^5.6.0
- react-markdown ^9.0.1
- recharts ^2.8.0
- rehype-katex ^7.0.0
- rehype-raw ^7.0.0
- rehype-sanitize ^6.0.0
- remark-gfm ^4.0.0
- remark-math ^6.0.0
- sonner ^2.0.7
- tailwind-merge ^2.6.0
- tailwindcss-animate ^1.0.7
- accelerate ==1.14.0
- numpy ==2.3.5
- pandas ==3.0.3
- torch ==2.11.0
- torchaudio ==2.11.0
- torchcodec ==0.14.0
- torchvision ==0.26.0
- transformers ==5.13.1
- aioprometheus >=23.12.0
- async-timeout *
- bcrypt >=4.0.0
- boto3 >=1.28.55,<1.28.65
- cachetools *
- click *
- fastapi >=0.110.3,<0.137
- gguf *
- huggingface-hub >=0.19.4
- imageio-ffmpeg *
- loguru *
- natsort *
- nvidia-ml-py *
- openai >1
- opencv-contrib-python-headless *
- opentelemetry-api >=1.20.0
- opentelemetry-exporter-otlp-proto-grpc >=1.20.0
- opentelemetry-exporter-otlp-proto-http >=1.20.0
- opentelemetry-instrumentation-fastapi >=0.41b0
- opentelemetry-instrumentation-httpx >=0.41b0
- opentelemetry-sdk >=1.20.0
- orjson *
- ormsgpack *
- pillow *
- protobuf *
- pydantic >2
- python-jose *
- python-multipart >=0.0.18
- requests *
- setproctitle *
- sse_starlette >=1.6.5
- tabulate *
- tqdm >=4.27
- typing_extensions *
- uv *
- uvicorn *
- xoscar >=0.7.2
- FlagEmbedding *
- accelerate >=0.28.0
- autoawq *
- bitsandbytes *
- controlnet_aux *
- einops *
- modelscope >=1.19.0
- optimum *
- peft <=0.17.1
- sentence-transformers >=3.1.0
- sentencepiece *
- tensorizer *
- tiktoken >=0.6.0
- timm *
- torch >=2.0.0
- torchaudio *
- transformers >=4.53.3
- transformers_stream_generator *
- ./.github/actions/check-release-permission * composite
- actions/checkout v6 composite
- actions/github-script 60a0d83039c74a4aee543508d2ffcb1c3799cdea composite
- docker/login-action v4 composite
- ChatTTS >=0.2.1
- HyperPyYAML *
- WeTextProcessing <1.0.4
- anyascii *
- argbind *
- cached_path *
- cn2an *
- conformer *
- datamodel_code_generator *
- diffusers >=0.32.0
- eva-decord *
- ffmpy *
- flatten_dict *
- fugashi *
- funasr ==1.2.7
- g2p_en *
- gdown *
- gruut *
- hydra-core >=1.3.2
- inflect *
- jieba *
- jj-pytorchvideo *
- json5 *
- jsonschema *
- julius *
- kokoro >=0.7.15
- langdetect *
- librosa *
- lightning >=2.0.0
- loralib *
- matplotlib *
- mecab-python3 *
- misaki >=0.7.15
- munch *
- nemo_text_processing <1.1.0
- num2words *
- omegaconf *
- onnxruntime ==1.16.0
- onnxruntime-gpu ==1.16.0
- pyarrow *
- pydub *
- pykakasi *
- pyloudnorm *
- pypinyin *
- pyworld >=0.3.4
- qwen-vl-utils *
- qwen_omni_utils *
- randomname *
- silero-vad *
- soundfile *
- tensorboard *
- tomli *
- torchdiffeq *
- unidic-lite *
- vector-quantize-pytorch <=1.17.3,>=1.14.24
- verovio >=4.3.1
- vocos *
- x_transformers >=1.31.14
- xxhash *
- node 20-slim build
- nvidia/cuda 13.0.2-devel-ubuntu22.04 build
- actions/github-script 60a0d83039c74a4aee543508d2ffcb1c3799cdea composite
- ./.github/actions/check-release-permission * composite
- actions/checkout v6 composite
- docker/build-push-action v7 composite
- docker/login-action v4 composite
- docker/setup-buildx-action v4 composite
- actions/stale v9 composite
- actions/checkout v4 composite
- actions/setup-python v5 composite
- docker.elastic.co/beats/filebeat 8.13.4
- 821 dependencies
- ${XINFERENCE_BYO_PYPISERVER_IMAGE -pypiserver/pypiserver
- ${XINFERENCE_IMAGE -xprobe/xinference
- ${XINFERENCE_IMAGE -xprobe/xinference
- ${XINFERENCE_PYPISERVER_IMAGE -xprobe/xinference-pypiserver
- ${XINFERENCE_GATEWAY_IMAGE -alpine/socat
- torch *
- accelerate ==1.13.0
- huggingface-hub ==0.36.2
- numpy ==2.2.6
- safetensors ==0.7.0
- soundfile ==0.13.1
- tiktoken ==0.12.0
- torch ==2.10.0
- transformers ==4.57.6
- numpy 1.23.4
- nvidia:
- pip 22.3.1
- python 3.10.8
- pytorch:
- torchvision 0.14.0
- argbind >=0.3.7
- descript-audiotools >=0.7.2
- einops *
- huggingface-hub *
- numpy *
- torch *
- torchaudio *
- tqdm *
- actions/checkout v4 composite
- actions/setup-python v5 composite
- actions/upload-artifact v4 composite
- argbind >=0.3.7
- descript-audiotools >=0.7.2
- einops *
- huggingface-hub *
- jupyterlab *
- numba >=0.5.7
- numpy *
- tensorboard *
- torch *
- torchaudio *
- tqdm *
- nvidia/cuda 10.2-cudnn7-runtime-ubuntu18.04 build
- torch >=1.2.0
- torchvision >=0.4.0
- actions/checkout v7 composite
- actions/setup-node v4 composite
- actions/upload-artifact v4 composite
- conda-incubator/setup-miniconda v3 composite
- actions/checkout v7 composite
- actions/setup-python v6 composite
- actions/checkout v7 composite
- astral-sh/setup-uv v6 composite