xinference 0.16.3__py3-none-any.whl → 1.2.1__py3-none-any.whl

{xinference-0.16.3.dist-info → xinference-1.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: xinference
-Version: 0.16.3
+Version: 1.2.1
 Summary: Model Serving Made Easy
 Home-page: https://github.com/xorbitsai/inference
 Author: Qin Xuye
@@ -19,7 +19,7 @@ Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Topic :: Software Development :: Libraries
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: xoscar>=0.3.0
+Requires-Dist: xoscar>=0.4.4
 Requires-Dist: torch
 Requires-Dist: gradio
 Requires-Dist: pillow
@@ -34,7 +34,7 @@ Requires-Dist: huggingface-hub>=0.19.4
 Requires-Dist: typing-extensions
 Requires-Dist: modelscope>=1.10.0
 Requires-Dist: sse-starlette>=1.6.5
-Requires-Dist: openai>1
+Requires-Dist: openai>=1.40.0
 Requires-Dist: python-jose[cryptography]
 Requires-Dist: passlib[bcrypt]
 Requires-Dist: aioprometheus[starlette]>=23.12.0
@@ -45,7 +45,7 @@ Requires-Dist: timm
 Requires-Dist: setproctitle
 Provides-Extra: all
 Requires-Dist: llama-cpp-python!=0.2.58,>=0.2.25; extra == "all"
-Requires-Dist: transformers>=4.43.2; extra == "all"
+Requires-Dist: transformers>=4.46.0; extra == "all"
 Requires-Dist: torch>=2.0.0; extra == "all"
 Requires-Dist: accelerate>=0.28.0; extra == "all"
 Requires-Dist: sentencepiece; extra == "all"
@@ -55,7 +55,6 @@ Requires-Dist: protobuf; extra == "all"
 Requires-Dist: einops; extra == "all"
 Requires-Dist: tiktoken>=0.6.0; extra == "all"
 Requires-Dist: sentence-transformers>=3.1.0; extra == "all"
-Requires-Dist: diffusers>=0.30.0; extra == "all"
 Requires-Dist: imageio-ffmpeg; extra == "all"
 Requires-Dist: controlnet-aux; extra == "all"
 Requires-Dist: orjson; extra == "all"
@@ -65,10 +64,8 @@ Requires-Dist: attrdict; extra == "all"
 Requires-Dist: timm>=0.9.16; extra == "all"
 Requires-Dist: torchvision; extra == "all"
 Requires-Dist: FlagEmbedding; extra == "all"
-Requires-Dist: funasr; extra == "all"
+Requires-Dist: funasr<1.1.17; extra == "all"
 Requires-Dist: omegaconf~=2.3.0; extra == "all"
-Requires-Dist: nemo-text-processing<1.1.0; extra == "all"
-Requires-Dist: WeTextProcessing<1.0.4; extra == "all"
 Requires-Dist: librosa; extra == "all"
 Requires-Dist: xxhash; extra == "all"
 Requires-Dist: torchaudio; extra == "all"
@@ -77,10 +74,12 @@ Requires-Dist: lightning>=2.0.0; extra == "all"
 Requires-Dist: hydra-core>=1.3.2; extra == "all"
 Requires-Dist: inflect; extra == "all"
 Requires-Dist: conformer; extra == "all"
+Requires-Dist: diffusers>=0.32.0; extra == "all"
+Requires-Dist: gguf; extra == "all"
 Requires-Dist: gdown; extra == "all"
 Requires-Dist: pyarrow; extra == "all"
 Requires-Dist: HyperPyYAML; extra == "all"
-Requires-Dist: onnxruntime==1.16.0; extra == "all"
+Requires-Dist: onnxruntime>=1.16.0; extra == "all"
 Requires-Dist: boto3<1.28.65,>=1.28.55; extra == "all"
 Requires-Dist: tensorizer~=2.9.0; extra == "all"
 Requires-Dist: eva-decord; extra == "all"
@@ -89,20 +88,33 @@ Requires-Dist: loguru; extra == "all"
 Requires-Dist: natsort; extra == "all"
 Requires-Dist: loralib; extra == "all"
 Requires-Dist: ormsgpack; extra == "all"
+Requires-Dist: cachetools; extra == "all"
+Requires-Dist: silero-vad; extra == "all"
+Requires-Dist: vector-quantize-pytorch<=1.17.3,>=1.14.24; extra == "all"
+Requires-Dist: torchdiffeq; extra == "all"
+Requires-Dist: x-transformers>=1.31.14; extra == "all"
+Requires-Dist: pypinyin; extra == "all"
+Requires-Dist: tomli; extra == "all"
+Requires-Dist: vocos; extra == "all"
+Requires-Dist: jieba; extra == "all"
+Requires-Dist: soundfile; extra == "all"
 Requires-Dist: qwen-vl-utils; extra == "all"
 Requires-Dist: datamodel-code-generator; extra == "all"
 Requires-Dist: jsonschema; extra == "all"
 Requires-Dist: verovio>=4.3.1; extra == "all"
 Requires-Dist: auto-gptq; sys_platform != "darwin" and extra == "all"
 Requires-Dist: autoawq<0.2.6; sys_platform != "darwin" and extra == "all"
-Requires-Dist: mlx-lm; (sys_platform == "darwin" and platform_machine == "arm64") and extra == "all"
+Requires-Dist: mlx-lm>=0.21.1; (sys_platform == "darwin" and platform_machine == "arm64") and extra == "all"
+Requires-Dist: mlx-vlm>=0.1.11; (sys_platform == "darwin" and platform_machine == "arm64") and extra == "all"
+Requires-Dist: mlx-whisper; (sys_platform == "darwin" and platform_machine == "arm64") and extra == "all"
+Requires-Dist: f5-tts-mlx; (sys_platform == "darwin" and platform_machine == "arm64") and extra == "all"
 Requires-Dist: vllm>=0.2.6; sys_platform == "linux" and extra == "all"
 Requires-Dist: sglang>=0.2.7; sys_platform == "linux" and extra == "all"
+Requires-Dist: nemo-text-processing<1.1.0; sys_platform == "linux" and extra == "all"
+Requires-Dist: WeTextProcessing<1.0.4; sys_platform == "linux" and extra == "all"
 Provides-Extra: audio
-Requires-Dist: funasr; extra == "audio"
+Requires-Dist: funasr<1.1.17; extra == "audio"
 Requires-Dist: omegaconf~=2.3.0; extra == "audio"
-Requires-Dist: nemo-text-processing<1.1.0; extra == "audio"
-Requires-Dist: WeTextProcessing<1.0.4; extra == "audio"
 Requires-Dist: librosa; extra == "audio"
 Requires-Dist: xxhash; extra == "audio"
 Requires-Dist: torchaudio; extra == "audio"
@@ -113,15 +125,37 @@ Requires-Dist: lightning>=2.0.0; extra == "audio"
 Requires-Dist: hydra-core>=1.3.2; extra == "audio"
 Requires-Dist: inflect; extra == "audio"
 Requires-Dist: conformer; extra == "audio"
-Requires-Dist: diffusers>=0.30.0; extra == "audio"
+Requires-Dist: diffusers>=0.32.0; extra == "audio"
 Requires-Dist: gdown; extra == "audio"
 Requires-Dist: pyarrow; extra == "audio"
 Requires-Dist: HyperPyYAML; extra == "audio"
-Requires-Dist: onnxruntime==1.16.0; extra == "audio"
+Requires-Dist: onnxruntime>=1.16.0; extra == "audio"
 Requires-Dist: loguru; extra == "audio"
 Requires-Dist: natsort; extra == "audio"
 Requires-Dist: loralib; extra == "audio"
 Requires-Dist: ormsgpack; extra == "audio"
+Requires-Dist: cachetools; extra == "audio"
+Requires-Dist: silero-vad; extra == "audio"
+Requires-Dist: vector-quantize-pytorch<=1.17.3,>=1.14.24; extra == "audio"
+Requires-Dist: torchdiffeq; extra == "audio"
+Requires-Dist: x-transformers>=1.31.14; extra == "audio"
+Requires-Dist: pypinyin; extra == "audio"
+Requires-Dist: tomli; extra == "audio"
+Requires-Dist: vocos; extra == "audio"
+Requires-Dist: jieba; extra == "audio"
+Requires-Dist: soundfile; extra == "audio"
+Requires-Dist: cached-path; extra == "audio"
+Requires-Dist: unidic-lite; extra == "audio"
+Requires-Dist: cn2an; extra == "audio"
+Requires-Dist: mecab-python3; extra == "audio"
+Requires-Dist: num2words; extra == "audio"
+Requires-Dist: pykakasi; extra == "audio"
+Requires-Dist: fugashi; extra == "audio"
+Requires-Dist: g2p-en; extra == "audio"
+Requires-Dist: anyascii; extra == "audio"
+Requires-Dist: gruut[de,es,fr]; extra == "audio"
+Requires-Dist: nemo-text-processing<1.1.0; sys_platform == "linux" and extra == "audio"
+Requires-Dist: WeTextProcessing<1.0.4; sys_platform == "linux" and extra == "audio"
 Provides-Extra: benchmark
 Requires-Dist: psutil; extra == "benchmark"
 Provides-Extra: dev
@@ -139,7 +173,7 @@ Requires-Dist: sphinx-intl>=0.9.9; extra == "dev"
 Requires-Dist: jieba>=0.42.0; extra == "dev"
 Requires-Dist: flake8>=3.8.0; extra == "dev"
 Requires-Dist: black; extra == "dev"
-Requires-Dist: openai>1; extra == "dev"
+Requires-Dist: openai>=1.40.0; extra == "dev"
 Requires-Dist: langchain; extra == "dev"
 Requires-Dist: langchain-community; extra == "dev"
 Requires-Dist: orjson; extra == "dev"
@@ -157,9 +191,10 @@ Requires-Dist: timm; extra == "doc"
 Provides-Extra: embedding
 Requires-Dist: sentence-transformers>=3.1.0; extra == "embedding"
 Provides-Extra: image
-Requires-Dist: diffusers>=0.30.0; extra == "image"
+Requires-Dist: diffusers>=0.32.0; extra == "image"
 Requires-Dist: controlnet-aux; extra == "image"
 Requires-Dist: deepcache; extra == "image"
+Requires-Dist: gguf; extra == "image"
 Requires-Dist: verovio>=4.3.1; extra == "image"
 Requires-Dist: transformers>=4.37.2; extra == "image"
 Requires-Dist: tiktoken>=0.6.0; extra == "image"
@@ -172,7 +207,12 @@ Requires-Dist: intel-extension-for-pytorch==2.1.10+xpu; extra == "intel"
 Provides-Extra: llama_cpp
 Requires-Dist: llama-cpp-python!=0.2.58,>=0.2.25; extra == "llama-cpp"
 Provides-Extra: mlx
-Requires-Dist: mlx-lm; extra == "mlx"
+Requires-Dist: mlx-lm>=0.21.1; extra == "mlx"
+Requires-Dist: mlx-vlm>=0.1.11; extra == "mlx"
+Requires-Dist: mlx-whisper; extra == "mlx"
+Requires-Dist: f5-tts-mlx; extra == "mlx"
+Requires-Dist: qwen-vl-utils; extra == "mlx"
+Requires-Dist: tomli; extra == "mlx"
 Provides-Extra: rerank
 Requires-Dist: FlagEmbedding; extra == "rerank"
 Provides-Extra: sglang
@@ -180,7 +220,7 @@ Requires-Dist: outlines>=0.0.34; extra == "sglang"
 Requires-Dist: sglang>=0.2.7; sys_platform == "linux" and extra == "sglang"
 Requires-Dist: vllm>=0.5.2; sys_platform == "linux" and extra == "sglang"
 Provides-Extra: transformers
-Requires-Dist: transformers>=4.43.2; extra == "transformers"
+Requires-Dist: transformers>=4.46.0; extra == "transformers"
 Requires-Dist: torch; extra == "transformers"
 Requires-Dist: accelerate>=0.28.0; extra == "transformers"
 Requires-Dist: sentencepiece; extra == "transformers"
@@ -202,7 +242,7 @@ Requires-Dist: jsonschema; extra == "transformers"
 Requires-Dist: auto-gptq; sys_platform != "darwin" and extra == "transformers"
 Requires-Dist: autoawq<0.2.6; sys_platform != "darwin" and extra == "transformers"
 Provides-Extra: video
-Requires-Dist: diffusers>=0.30.0; extra == "video"
+Requires-Dist: diffusers>=0.32.0; extra == "video"
 Requires-Dist: imageio-ffmpeg; extra == "video"
 Provides-Extra: vllm
 Requires-Dist: vllm>=0.2.6; extra == "vllm"
@@ -222,7 +262,7 @@ Requires-Dist: vllm>=0.2.6; extra == "vllm"
 [![PyPI Latest Release](https://img.shields.io/pypi/v/xinference.svg?style=for-the-badge)](https://pypi.org/project/xinference/)
 [![License](https://img.shields.io/pypi/l/xinference.svg?style=for-the-badge)](https://github.com/xorbitsai/inference/blob/main/LICENSE)
 [![Build Status](https://img.shields.io/github/actions/workflow/status/xorbitsai/inference/python.yaml?branch=main&style=for-the-badge&label=GITHUB%20ACTIONS&logo=github)](https://actions-badge.atrox.dev/xorbitsai/inference/goto?ref=main)
-[![Slack](https://img.shields.io/badge/join_Slack-781FF5.svg?logo=slack&style=for-the-badge)](https://join.slack.com/t/xorbitsio/shared_invite/zt-1o3z9ucdh-RbfhbPVpx7prOVdM1CAuxg)
+[![Discord](https://img.shields.io/badge/join_Discord-5462eb.svg?logo=discord&style=for-the-badge&logoColor=%23f5f5f5)](https://discord.gg/Xw9tszSkr5)
 [![Twitter](https://img.shields.io/twitter/follow/xorbitsio?logo=x&style=for-the-badge)](https://twitter.com/xorbitsio)
 
 <p align="center">
@@ -242,11 +282,12 @@ researcher, developer, or data scientist, Xorbits Inference empowers you to unle
 potential of cutting-edge AI models.
 
 <div align="center">
-<i><a href="https://join.slack.com/t/xorbitsio/shared_invite/zt-1z3zsm9ep-87yI9YZ_B79HLB2ccTq4WA">👉 Join our Slack community!</a></i>
+<i><a href="https://discord.gg/Xw9tszSkr5">👉 Join our Discord community!</a></i>
 </div>
 
 ## 🔥 Hot Topics
 ### Framework Enhancements
+- VLLM enhancement: Shared KV cache across multiple replicas: [#2732](https://github.com/xorbitsai/inference/pull/2732)
 - Support Continuous batching for Transformers engine: [#1724](https://github.com/xorbitsai/inference/pull/1724)
 - Support MLX backend for Apple Silicon chips: [#1765](https://github.com/xorbitsai/inference/pull/1765)
 - Support specifying worker and GPU indexes for launching models: [#1195](https://github.com/xorbitsai/inference/pull/1195)
@@ -255,19 +296,20 @@ potential of cutting-edge AI models.
 - Support speech recognition model: [#929](https://github.com/xorbitsai/inference/pull/929)
 - Metrics support: [#906](https://github.com/xorbitsai/inference/pull/906)
 ### New Models
-- Built-in support for [Qwen 2.5 Series](https://qwenlm.github.io/blog/qwen2.5/): [#2325](https://github.com/xorbitsai/inference/pull/2325)
-- Built-in support for [Fish Speech V1.4](https://huggingface.co/fishaudio/fish-speech-1.4): [#2295](https://github.com/xorbitsai/inference/pull/2295)
-- Built-in support for [DeepSeek-V2.5](https://huggingface.co/deepseek-ai/DeepSeek-V2.5): [#2292](https://github.com/xorbitsai/inference/pull/2292)
-- Built-in support for [Qwen2-Audio](https://github.com/QwenLM/Qwen2-Audio): [#2271](https://github.com/xorbitsai/inference/pull/2271)
-- Built-in support for [Qwen2-vl-instruct](https://github.com/QwenLM/Qwen2-VL): [#2205](https://github.com/xorbitsai/inference/pull/2205)
-- Built-in support for [MiniCPM3-4B](https://huggingface.co/openbmb/MiniCPM3-4B): [#2263](https://github.com/xorbitsai/inference/pull/2263)
-- Built-in support for [CogVideoX](https://github.com/THUDM/CogVideo): [#2049](https://github.com/xorbitsai/inference/pull/2049)
-- Built-in support for [flux.1-schnell & flux.1-dev](https://www.basedlabs.ai/tools/flux1): [#2007](https://github.com/xorbitsai/inference/pull/2007)
+- Built-in support for [MeloTTS](https://github.com/myshell-ai/MeloTTS): [#2760](https://github.com/xorbitsai/inference/pull/2760)
+- Built-in support for [CogAgent](https://github.com/THUDM/CogAgent): [#2740](https://github.com/xorbitsai/inference/pull/2740)
+- Built-in support for [HunyuanVideo](https://github.com/Tencent/HunyuanVideo): [#2721](https://github.com/xorbitsai/inference/pull/2721)
+- Built-in support for [HunyuanDiT](https://github.com/Tencent/HunyuanDiT): [#2727](https://github.com/xorbitsai/inference/pull/2727)
+- Built-in support for [Macro-o1](https://github.com/AIDC-AI/Marco-o1): [#2749](https://github.com/xorbitsai/inference/pull/2749)
+- Built-in support for [Stable Diffusion 3.5](https://huggingface.co/collections/stabilityai/stable-diffusion-35-671785cca799084f71fa2838): [#2706](https://github.com/xorbitsai/inference/pull/2706)
+- Built-in support for [CosyVoice 2](https://huggingface.co/FunAudioLLM/CosyVoice2-0.5B): [#2684](https://github.com/xorbitsai/inference/pull/2684)
+- Built-in support for [Fish Speech V1.5](https://huggingface.co/fishaudio/fish-speech-1.5): [#2672](https://github.com/xorbitsai/inference/pull/2672)
 ### Integrations
 - [Dify](https://docs.dify.ai/advanced/model-configuration/xinference): an LLMOps platform that enables developers (and even non-developers) to quickly build useful applications based on large language models, ensuring they are visual, operable, and improvable.
 - [FastGPT](https://github.com/labring/FastGPT): a knowledge-based platform built on the LLM, offers out-of-the-box data processing and model invocation capabilities, allows for workflow orchestration through Flow visualization.
-- [Chatbox](https://chatboxai.app/): a desktop client for multiple cutting-edge LLM models, available on Windows, Mac and Linux.
 - [RAGFlow](https://github.com/infiniflow/ragflow): is an open-source RAG engine based on deep document understanding.
+- [MaxKB](https://github.com/1Panel-dev/MaxKB): MaxKB = Max Knowledge Base, it is a chatbot based on Large Language Models (LLM) and Retrieval-Augmented Generation (RAG). 
+- [Chatbox](https://chatboxai.app/): a desktop client for multiple cutting-edge LLM models, available on Windows, Mac and Linux.
 
 
 ## Key Features
@@ -383,11 +425,29 @@ Once Xinference is running, there are multiple ways you can try it: via the web
 
 ## Getting involved
 
-| Platform                                                                                      | Purpose                                            |
-|-----------------------------------------------------------------------------------------------|----------------------------------------------------|
-| [Github Issues](https://github.com/xorbitsai/inference/issues)                                | Reporting bugs and filing feature requests.        |
-| [Slack](https://join.slack.com/t/xorbitsio/shared_invite/zt-1o3z9ucdh-RbfhbPVpx7prOVdM1CAuxg) | Collaborating with other Xorbits users.            |
-| [Twitter](https://twitter.com/xorbitsio)                                                      | Staying up-to-date on new features.                |
+| Platform                                                                                        | Purpose                                     |
+|-------------------------------------------------------------------------------------------------|---------------------------------------------|
+| [Github Issues](https://github.com/xorbitsai/inference/issues)                                  | Reporting bugs and filing feature requests. |
+| [Discord](https://discord.gg/Xw9tszSkr5) | Collaborating with other Xinference users.  |
+| [Twitter](https://twitter.com/xorbitsio)                                                        | Staying up-to-date on new features.         |
+
+## Citation
+
+If this work is helpful, please kindly cite as:
+
+```bibtex
+@inproceedings{lu2024xinference,
+    title = "Xinference: Making Large Model Serving Easy",
+    author = "Lu, Weizheng and Xiong, Lingfeng and Zhang, Feng and Qin, Xuye and Chen, Yueguo",
+    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
+    month = nov,
+    year = "2024",
+    address = "Miami, Florida, USA",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2024.emnlp-demo.30",
+    pages = "291--300",
+}
+```
 
 ## Contributors