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, 08:00 UTC
Change image urls (#164)
Zhuohan Li committed
Jun 20, 2023 at 11:15 UTC
fc72e39de33ed854360cd4ada18f97b236f2de85
1 file changed
+7
-7
README.md
+7
-7
@@ -1,7 +1,7 @@
1
<p align="center">
2
<picture>
3
- <source media="(prefers-color-scheme: dark)" srcset="./docs/source/assets/logos/vllm-logo-text-dark.png">
4
- <img alt="vLLM" src="./docs/source/assets/logos/vllm-logo-text-light.png" width=55%>
3
+ <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vllm-project/vllm/main/docs/source/assets/logos/vllm-logo-text-dark.png">
4
+ <img alt="vLLM" src="https://raw.githubusercontent.com/vllm-project/vllm/main/docs/source/assets/logos/vllm-logo-text-light.png" width=55%>
5
</picture>
6
</p>
7
@@ -66,12 +66,12 @@ For details, check out our [blog post]().
66
67
<p align="center">
68
<picture>
69
- <source media="(prefers-color-scheme: dark)" srcset="./docs/source/assets/figures/perf_a10g_n1_dark.png">
70
- <img src="./docs/source/assets/figures/perf_a10g_n1_light.png" width="45%">
69
+ <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vllm-project/vllm/main/docs/source/assets/figures/perf_a10g_n1_dark.png">
70
+ <img src="https://raw.githubusercontent.com/vllm-project/vllm/main/docs/source/assets/figures/perf_a10g_n1_light.png" width="45%">
71
</picture>
72
<picture>
73
<source media="(prefers-color-scheme: dark)" srcset="./docs/source/assets/figures/perf_a100_n1_dark.png">
74
- <img src="./docs/source/assets/figures/perf_a100_n1_light.png" width="45%">
74
+ <img src="https://raw.githubusercontent.com/vllm-project/vllm/main/docs/source/assets/figures/perf_a100_n1_light.png" width="45%">
75
</picture>
76
<br>
77
<em> Serving throughput when each request asks for 1 output completion. </em>
@@ -80,11 +80,11 @@ For details, check out our [blog post]().
80
<p align="center">
81
<picture>
82
<source media="(prefers-color-scheme: dark)" srcset="./docs/source/assets/figures/perf_a10g_n3_dark.png">
83
- <img src="./docs/source/assets/figures/perf_a10g_n3_light.png" width="45%">
83
+ <img src="https://raw.githubusercontent.com/vllm-project/vllm/main/docs/source/assets/figures/perf_a10g_n3_light.png" width="45%">
84
</picture>
85
<picture>
86
<source media="(prefers-color-scheme: dark)" srcset="./docs/source/assets/figures/perf_a100_n3_dark.png">
87
- <img src="./docs/source/assets/figures/perf_a100_n3_light.png" width="45%">
87
+ <img src="https://raw.githubusercontent.com/vllm-project/vllm/main/docs/source/assets/figures/perf_a100_n3_light.png" width="45%">
88
</picture> <br>
89
<em> Serving throughput when each request asks for 3 output completions. </em>
90
</p>