/vllm-gptq

A high-throughput and memory-efficient inference and serving engine for LLMs

Primary LanguagePythonApache License 2.0Apache-2.0

vLLM

Easy, fast, and cheap LLM serving for everyone

| Documentation | Blog | Paper | Discord |

GPTQ support has been merged into vLLM, please use the official vLLM build instead.

This repo currently supports a varieties of other quantization methods including:

  • GGUF

Llama (including mistral, yi), mixtral and qwen1.5 are supported for now.

python -m vllm.entrypoints.api_server --model miqu-1-70b.q2_K.gguf
  • EXL2

Llama, Mixtral, Qwen1.5, Gemma, StarCoder2, Orion and Command-r are tested.

python -m vllm.entrypoints.api_server --model LoneStriker/Qwen1.5-14B-Chat-3.0bpw-h6-exl2 --quantization exl2 --dtype half
  • QUIP#

SOTA 2-bit models quantized using QuIP-for-all. Only support tensor_parallel_size=1.

  • Better performance for GPTQ & AWQ

We extend the marlin kernel to desc-act GPTQ model as well as AWQ model with zero points, and repack the model on the fly. Following the latency for 256 input size and 256 output size with Mistral-7B quants.

Batch AWQ-main AWQ-this GPTQ-main GPTQ-this
1 2.42 1.45 1.43 1.76
4 2.62 1.65 2.01 1.98
16 3.58 2.38 4.77 2.74
64 8.91 5.94 10.46 6.44
256 30.85 23.03 24.81 24.40

The Third vLLM Bay Area Meetup (April 2nd 6pm-8:30pm PT)

We are thrilled to announce our third vLLM Meetup! The vLLM team will share recent updates and roadmap. We will also have vLLM collaborators from Roblox coming up to the stage to discuss their experience in deploying LLMs with vLLM. Please register here and join us!

Latest News 🔥

  • [2024/01] We hosted the second vLLM meetup in SF! Please find the meetup slides here.
  • [2024/01] Added ROCm 6.0 support to vLLM.
  • [2023/12] Added ROCm 5.7 support to vLLM.
  • [2023/10] We hosted the first vLLM meetup in SF! Please find the meetup slides here.
  • [2023/09] We created our Discord server! Join us to discuss vLLM and LLM serving! We will also post the latest announcements and updates there.
  • [2023/09] We released our PagedAttention paper on arXiv!
  • [2023/08] We would like to express our sincere gratitude to Andreessen Horowitz (a16z) for providing a generous grant to support the open-source development and research of vLLM.
  • [2023/07] Added support for LLaMA-2! You can run and serve 7B/13B/70B LLaMA-2s on vLLM with a single command!
  • [2023/06] Serving vLLM On any Cloud with SkyPilot. Check out a 1-click example to start the vLLM demo, and the blog post for the story behind vLLM development on the clouds.
  • [2023/06] We officially released vLLM! FastChat-vLLM integration has powered LMSYS Vicuna and Chatbot Arena since mid-April. Check out our blog post.

About

vLLM is a fast and easy-to-use library for LLM inference and serving.

vLLM is fast with:

  • State-of-the-art serving throughput
  • Efficient management of attention key and value memory with PagedAttention
  • Continuous batching of incoming requests
  • Fast model execution with CUDA/HIP graph
  • Quantization: GPTQ, AWQ, SqueezeLLM, FP8 KV Cache
  • Optimized CUDA kernels

vLLM is flexible and easy to use with:

  • Seamless integration with popular Hugging Face models
  • High-throughput serving with various decoding algorithms, including parallel sampling, beam search, and more
  • Tensor parallelism support for distributed inference
  • Streaming outputs
  • OpenAI-compatible API server
  • Support NVIDIA GPUs and AMD GPUs
  • (Experimental) Prefix caching support
  • (Experimental) Multi-lora support

vLLM seamlessly supports many Hugging Face models, including the following architectures:

  • Aquila & Aquila2 (BAAI/AquilaChat2-7B, BAAI/AquilaChat2-34B, BAAI/Aquila-7B, BAAI/AquilaChat-7B, etc.)
  • Baichuan & Baichuan2 (baichuan-inc/Baichuan2-13B-Chat, baichuan-inc/Baichuan-7B, etc.)
  • BLOOM (bigscience/bloom, bigscience/bloomz, etc.)
  • ChatGLM (THUDM/chatglm2-6b, THUDM/chatglm3-6b, etc.)
  • Command-R (CohereForAI/c4ai-command-r-v01, etc.)
  • DBRX (databricks/dbrx-base, databricks/dbrx-instruct etc.)
  • DeciLM (Deci/DeciLM-7B, Deci/DeciLM-7B-instruct, etc.)
  • Falcon (tiiuae/falcon-7b, tiiuae/falcon-40b, tiiuae/falcon-rw-7b, etc.)
  • Gemma (google/gemma-2b, google/gemma-7b, etc.)
  • GPT-2 (gpt2, gpt2-xl, etc.)
  • GPT BigCode (bigcode/starcoder, bigcode/gpt_bigcode-santacoder, etc.)
  • GPT-J (EleutherAI/gpt-j-6b, nomic-ai/gpt4all-j, etc.)
  • GPT-NeoX (EleutherAI/gpt-neox-20b, databricks/dolly-v2-12b, stabilityai/stablelm-tuned-alpha-7b, etc.)
  • InternLM (internlm/internlm-7b, internlm/internlm-chat-7b, etc.)
  • InternLM2 (internlm/internlm2-7b, internlm/internlm2-chat-7b, etc.)
  • Jais (core42/jais-13b, core42/jais-13b-chat, core42/jais-30b-v3, core42/jais-30b-chat-v3, etc.)
  • LLaMA & LLaMA-2 (meta-llama/Llama-2-70b-hf, lmsys/vicuna-13b-v1.3, young-geng/koala, openlm-research/open_llama_13b, etc.)
  • Mistral (mistralai/Mistral-7B-v0.1, mistralai/Mistral-7B-Instruct-v0.1, etc.)
  • Mixtral (mistralai/Mixtral-8x7B-v0.1, mistralai/Mixtral-8x7B-Instruct-v0.1, etc.)
  • MPT (mosaicml/mpt-7b, mosaicml/mpt-30b, etc.)
  • OLMo (allenai/OLMo-1B, allenai/OLMo-7B, etc.)
  • OPT (facebook/opt-66b, facebook/opt-iml-max-30b, etc.)
  • Orion (OrionStarAI/Orion-14B-Base, OrionStarAI/Orion-14B-Chat, etc.)
  • Phi (microsoft/phi-1_5, microsoft/phi-2, etc.)
  • Qwen (Qwen/Qwen-7B, Qwen/Qwen-7B-Chat, etc.)
  • Qwen2 (Qwen/Qwen2-7B-beta, Qwen/Qwen-7B-Chat-beta, etc.)
  • Qwen2MoE (Qwen/Qwen1.5-MoE-A2.7B, Qwen/Qwen1.5-MoE-A2.7B-Chat, etc.)
  • StableLM(stabilityai/stablelm-3b-4e1t, stabilityai/stablelm-base-alpha-7b-v2, etc.)
  • Starcoder2(bigcode/starcoder2-3b, bigcode/starcoder2-7b, bigcode/starcoder2-15b, etc.)
  • Xverse (xverse/XVERSE-7B-Chat, xverse/XVERSE-13B-Chat, xverse/XVERSE-65B-Chat, etc.)
  • Yi (01-ai/Yi-6B, 01-ai/Yi-34B, etc.)

Install vLLM with pip or from source:

pip install vllm

Getting Started

Visit our documentation to get started.

Contributing

We welcome and value any contributions and collaborations. Please check out CONTRIBUTING.md for how to get involved.

Citation

If you use vLLM for your research, please cite our paper:

@inproceedings{kwon2023efficient,
  title={Efficient Memory Management for Large Language Model Serving with PagedAttention},
  author={Woosuk Kwon and Zhuohan Li and Siyuan Zhuang and Ying Sheng and Lianmin Zheng and Cody Hao Yu and Joseph E. Gonzalez and Hao Zhang and Ion Stoica},
  booktitle={Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles},
  year={2023}
}