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, 04:15 UTC
Update requirements-dev.txt to include package for benchmarking scripts. (#3181)
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
Chen Wang committed
Mar 7, 2024 at 03:39 UTC
cbf4c05b156c8705c6bb1a94b9edc0a5b4d26e20
1 file changed
+3
requirements-dev.txt
+3
@@ -21,3 +21,6 @@ einops # required for MPT
21
openai
22
requests
23
ray
24
+
25
+# Benchmarking
26
+aiohttp