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][ROCm] Install arctic-inference on ROCm tests (#29344)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Divakar Verma committed
Nov 24, 2025 at 20:15 UTC
22b42b5402f887c7d4b9f9aa4e82c970a6fd11a9
1 file changed
+3
requirements/rocm-test.txt
+3
@@ -45,3 +45,6 @@ multiprocess==0.70.16
45
46
# Plugins test
47
terratorch @ git+https://github.com/IBM/terratorch.git@07184fcf91a1324f831ff521dd238d97fe350e3e
48
+
49
+# Required for suffix decoding test
50
+arctic-inference == 0.1.1
\ No newline at end of file