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 10, 19:00 UTC
[CI] Bump sentence-transformer from 3.2.1 to 5.2.0 (#31664)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
wang.yuqi committed
Jan 5, 2026 at 13:45 UTC
76fd458aa7cee8e2f93481be9aac1678776c404f
3 files changed
+4
-4
requirements/nightly_torch_test.txt
+1
-1
@@ -17,7 +17,7 @@ vocos # required for minicpmo_26 test
17
peft
18
pqdm
19
ray[cgraph,default]>=2.48.0 # Ray Compiled Graph, required by pipeline parallelism tests
20
-sentence-transformers # required for embedding tests
20
+sentence-transformers>=5.2.0 # required for embedding tests
21
soundfile # required for audio tests
22
jiwer # required for audio tests
23
timm # required for internvl test
requirements/test.in
+1
-1
@@ -19,7 +19,7 @@ vocos # required for minicpmo_26 test
19
peft>=0.15.0 # required for phi-4-mm test
20
pqdm
21
ray[cgraph,default]>=2.48.0 # Ray Compiled Graph, required by pipeline parallelism tests
22
-sentence-transformers # required for embedding tests
22
+sentence-transformers>=5.2.0 # required for embedding tests
23
soundfile # required for audio tests
24
jiwer # required for audio tests
25
tblib # for pickling test exceptions
requirements/test.txt
+2
-2
@@ -723,7 +723,6 @@ pillow==10.4.0
723
# perceptron
724
# scikit-image
725
# segmentation-models-pytorch
726
- # sentence-transformers
726
# torchgeo
727
# torchvision
728
platformdirs==4.3.6
@@ -1023,7 +1022,7 @@ segmentation-models-pytorch==0.4.0
1022
# via
1023
# terratorch
1024
# torchgeo
1026
-sentence-transformers==3.2.1
1025
+sentence-transformers==5.2.0
1026
# via
1027
# -r requirements/test.in
1028
# mteb
@@ -1263,6 +1262,7 @@ typing-extensions==4.15.0
1262
# pydantic-core
1263
# pydantic-extra-types
1264
# pytorch-lightning
1265
+ # sentence-transformers
1266
# sqlalchemy
1267
# torch
1268
# torchgeo