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 15, 14:45 UTC
Don't install triton on `ppc64le` platform (#16470)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Apr 11, 2025 at 11:11 UTC
51baa9c333a348915dca5d6a2eca0d6037751874
1 file changed
+1
-1
requirements/cpu.txt
+1
-1
@@ -17,4 +17,4 @@ torchvision==0.21.0; platform_machine == "ppc64le"
17
datasets # for benchmark scripts
18
19
# cpu cannot use triton 3.3.0
20
-triton==3.2.0
20
+triton==3.2.0; platform_machine != "ppc64le"