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, 06:00 UTC
[CI/Build] Fix torch nightly CI dependencies (#19505)
Signed-off-by: Richard Zou <zou3519@gmail.com>
Richard Zou committed
Jun 11, 2025 at 17:40 UTC
42f52cc95bf34a2e15f4cdbc8474503a9bcc970f
1 file changed
+2
-2
requirements/nightly_torch_test.txt
+2
-2
@@ -10,7 +10,7 @@ pytest-timeout
10
11
librosa # required by audio tests in entrypoints/openai
12
sentence-transformers # required for embedding tests
13
-transformers==4.51.3
13
+transformers==4.52.4
14
transformers_stream_generator # required for qwen-vl test
15
numba == 0.61.2; python_version > '3.9'
16
# testing utils
@@ -42,5 +42,5 @@ num2words # required for smolvlm test
42
pqdm
43
timm # required for internvl test
44
45
-schemathesis>=3.39.15 # Required for openai schema test.
45
+schemathesis==3.39.15 # Required for openai schema test.
46
mteb>=1.38.11, <2 # required for mteb test