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, 00:30 UTC
[Docs] Add acknowledgment for sponsors (#4925)
Simon Mo committed
May 21, 2024 at 00:17 UTC
e941f885843d4bcd239f805a9267729e9631556f
3 files changed
+50
README.md
+25
@@ -87,6 +87,31 @@ Visit our [documentation](https://vllm.readthedocs.io/en/latest/) to learn more.
87
We welcome and value any contributions and collaborations.
88
Please check out [CONTRIBUTING.md](./CONTRIBUTING.md) for how to get involved.
89
90
+## Sponsors
91
+
92
+vLLM is a community project. Our compute resources for development and testing are supported by the following organizations. Thank you for your support!
93
+
94
+<!-- Note: Please sort them in alphabetical order. -->
95
+<!-- Note: Please keep these consistent with docs/source/community/sponsors.md -->
96
+
97
+- a16z
98
+- AMD
99
+- Anyscale
100
+- AWS
101
+- Crusoe Cloud
102
+- Databricks
103
+- DeepInfra
104
+- Lambda Lab
105
+- NVIDIA
106
+- Replicate
107
+- Roblox
108
+- RunPod
109
+- Trainy
110
+- UC Berkeley
111
+- UC San Diego
112
+
113
+We also have an official fundraising venue through [OpenCollective](https://opencollective.com/vllm). We plan to use the fund to support the development, maintenance, and adoption of vLLM.
114
+
115
## Citation
116
117
If you use vLLM for your research, please cite our [paper](https://arxiv.org/abs/2309.06180):
docs/source/community/sponsors.md
new
+24
@@ -0,0 +1,24 @@
1
+# Sponsors
2
+
3
+vLLM is a community project. Our compute resources for development and testing are supported by the following organizations. Thank you for your support!
4
+
5
+<!-- Note: Please sort them in alphabetical order. -->
6
+<!-- Note: Please keep these consistent with README.md. -->
7
+
8
+- a16z
9
+- AMD
10
+- Anyscale
11
+- AWS
12
+- Crusoe Cloud
13
+- Databricks
14
+- DeepInfra
15
+- Lambda Lab
16
+- NVIDIA
17
+- Replicate
18
+- Roblox
19
+- RunPod
20
+- Trainy
21
+- UC Berkeley
22
+- UC San Diego
23
+
24
+We also have an official fundraising venue through [OpenCollective](https://opencollective.com/vllm). We plan to use the fund to support the development, maintenance, and adoption of vLLM.
\ No newline at end of file
docs/source/index.rst
+1
@@ -118,6 +118,7 @@ Documentation
118
:caption: Community
119
120
community/meetups
121
+ community/sponsors
122
123
Indices and tables
124
==================