@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / eda1a7cad3
Fork 0

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

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 17, 06:45 UTC

Announce paper release (#1036)

Woosuk Kwon committed Sep 13, 2023 at 17:38 UTC eda1a7cad3b58d33353ce8f4145c66237a65c238
2 files changed +15 -1
README.md
+14 -1
@@ -10,13 +10,14 @@ Easy, fast, and cheap LLM serving for everyone
10 </h3>
11
12 <p align="center">
13 -| <a href="https://vllm.readthedocs.io/en/latest/"><b>Documentation</b></a> | <a href="https://vllm.ai"><b>Blog</b></a> | <a href="https://github.com/vllm-project/vllm/discussions"><b>Discussions</b></a> |
13 +| <a href="https://vllm.readthedocs.io/en/latest/"><b>Documentation</b></a> | <a href="https://vllm.ai"><b>Blog</b></a> | <a href="https://arxiv.org/abs/2309.06180"><b>Paper</b></a> | <a href="https://github.com/vllm-project/vllm/discussions"><b>Discussions</b></a> |
14
15 </p>
16
17 ---
18
19 *Latest News* 🔥
20 +- [2023/09] We released our [PagedAttention paper](https://arxiv.org/abs/2309.06180) on arXiv!
21 - [2023/08] We would like to express our sincere gratitude to [Andreessen Horowitz](https://a16z.com/2023/08/30/supporting-the-open-source-ai-community/) (a16z) for providing a generous grant to support the open-source development and research of vLLM.
22 - [2023/07] Added support for LLaMA-2! You can run and serve 7B/13B/70B LLaMA-2s on vLLM with a single command!
23 - [2023/06] Serving vLLM On any Cloud with SkyPilot. Check out a 1-click [example](https://github.com/skypilot-org/skypilot/blob/master/llm/vllm) to start the vLLM demo, and the [blog post](https://blog.skypilot.co/serving-llm-24x-faster-on-the-cloud-with-vllm-and-skypilot/) for the story behind vLLM development on the clouds.
@@ -104,3 +105,15 @@ For details, check out our [blog post](https://vllm.ai).
105
106 We welcome and value any contributions and collaborations.
107 Please check out [CONTRIBUTING.md](./CONTRIBUTING.md) for how to get involved.
108 +
109 +## Citation
110 +
111 +If you use vLLM for your research, please cite our [paper](https://arxiv.org/abs/2309.06180):
112 +```bibtex
113 +@inproceedings{kwon2023efficient,
114 + title={Efficient Memory Management for Large Language Model Serving with PagedAttention},
115 + 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},
116 + booktitle={Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles},
117 + year={2023}
118 +}
119 +```
docs/source/index.rst
+1
@@ -43,6 +43,7 @@ vLLM is flexible and easy to use with:
43 For more information, check out the following:
44
45 * `vLLM announcing blog post <https://vllm.ai>`_ (intro to PagedAttention)
46 +* `vLLM paper <https://arxiv.org/abs/2309.06180>`_ (SOSP 2023)
47 * `How continuous batching enables 23x throughput in LLM inference while reducing p50 latency <https://www.anyscale.com/blog/continuous-batching-llm-inference>`_ by Cade Daniel et al.
48
49