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, 00:15 UTC
[CI/Build] Fix dependency conflict between model-hosting-container-standards and starlette (#32560)
Signed-off-by: Daniel Mescheder <dmesch@amazon.com> Co-authored-by: Daniel Mescheder <dmesch@amazon.com>
Daniel Mescheder committed
Jan 19, 2026 at 12:27 UTC
cdd03d25d3207d96bd8dee919632b9db090b83c8
1 file changed
+5
-2
requirements/test.txt
+5
-2
@@ -32,6 +32,8 @@ albumentations==1.4.6
32
# terratorch
33
alembic==1.16.4
34
# via mlflow
35
+annotated-doc==0.0.4
36
+ # via fastapi
37
annotated-types==0.7.0
38
# via pydantic
39
antlr4-python3-runtime==4.9.3
@@ -206,7 +208,7 @@ encodec==0.1.1
208
# via vocos
209
evaluate==0.4.3
210
# via lm-eval
209
-fastapi==0.116.1
211
+fastapi==0.128.0
212
# via
213
# gpt-oss
214
# mlflow-skinny
@@ -1077,7 +1079,7 @@ sqlitedict==2.1.0
1079
# via lm-eval
1080
sqlparse==0.5.3
1081
# via mlflow-skinny
1080
-starlette==0.46.2
1082
+starlette==0.50.0
1083
# via
1084
# fastapi
1085
# schemathesis
@@ -1267,6 +1269,7 @@ typing-extensions==4.15.0
1269
# pytorch-lightning
1270
# sentence-transformers
1271
# sqlalchemy
1272
+ # starlette
1273
# torch
1274
# torchgeo
1275
# typer