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 14, 05:30 UTC
[ROCm] enable some tests in entrypoints test groups on AMD (#26725)
Signed-off-by: Yida <yida.wu@amd.com>
Concurrensee committed
Oct 20, 2025 at 19:37 UTC
58fbbcb2f5983fac9436f7f520f8485271c59488
1 file changed
+6
-2
requirements/rocm-test.txt
+6
-2
@@ -1,6 +1,8 @@
1
# Common dependencies
2
-r common.txt
3
tblib==3.1.0
4
+bm25s==0.2.13
5
+pystemmer==3.0.0
6
7
# entrypoints test
8
# librosa==0.10.2.post1 # required by audio tests in entrypoints/openai
@@ -29,6 +31,8 @@ matplotlib==3.10.3
31
# Multi-Modal Models Test (Extended) 3
32
blobfile==3.0.0
33
32
-schemathesis==3.39.15 # Required for openai schema test.
34
+# Required for openai schema test.
35
+schemathesis==3.39.15
36
34
-mteb[bm25s]>=1.38.11, <2 # required for mteb test
37
+# required for mteb test
38
+mteb[bm25s]>=1.38.11, <2