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, 23:45 UTC
[Bugfix][CI/Build] Update peft version in test requirement (#21729)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Isotr0py committed
Jul 28, 2025 at 21:17 UTC
31084b3b1fbc925f0946cd4a2257a37a9c2a7607
2 files changed
+2
-2
requirements/test.in
+1
-1
@@ -15,7 +15,7 @@ httpx
15
librosa # required for audio tests
16
vector_quantize_pytorch # required for minicpmo_26 test
17
vocos # required for minicpmo_26 test
18
-peft
18
+peft>=0.15.0 # required for phi-4-mm test
19
pqdm
20
ray[cgraph,default]>=2.43.0, !=2.44.* # Ray Compiled Graph, required by pipeline parallelism tests
21
sentence-transformers # required for embedding tests
requirements/test.txt
+1
-1
@@ -661,7 +661,7 @@ pathvalidate==3.2.1
661
# via pytablewriter
662
patsy==1.0.1
663
# via statsmodels
664
-peft==0.13.2
664
+peft==0.16.0
665
# via
666
# -r requirements/test.in
667
# lm-eval