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, 03:00 UTC
[Hardware][CPU] Update cpu torch to match default of 2.2.1 (#3854)
Michael Goin committed
Apr 4, 2024 at 12:49 UTC
db2a6a41e206abecf4128aba25117fcaf7bebe12
1 file changed
+1
-1
requirements-cpu.txt
+1
-1
@@ -9,7 +9,7 @@ fastapi
9
uvicorn[standard]
10
pydantic >= 2.0 # Required for OpenAI server.
11
prometheus_client >= 0.18.0
12
-torch == 2.1.2+cpu
12
+torch == 2.2.1+cpu
13
triton >= 2.1.0
14
filelock == 3.13.3
15
py-cpuinfo
\ No newline at end of file