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 12, 14:45 UTC
[CI/Build] Pin torchgeo dependency for AMD (#29353)
Signed-off-by: Ryan Rock <ryan.rock@amd.com>
Ryan Rock committed
Nov 25, 2025 at 01:14 UTC
fe3a4f5b347c64f1d5f2cb10990437a56f720660
1 file changed
+2
-1
requirements/rocm-test.txt
+2
-1
@@ -45,6 +45,7 @@ multiprocess==0.70.16
45
46
# Plugins test
47
terratorch @ git+https://github.com/IBM/terratorch.git@07184fcf91a1324f831ff521dd238d97fe350e3e
48
+torchgeo==0.7.0
49
50
# Required for suffix decoding test
50
-arctic-inference == 0.1.1
\ No newline at end of file
51
+arctic-inference == 0.1.1