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 8, 12:30 UTC
Patch protobuf for CVE-2026-0994 (#34253)
Signed-off-by: Seiji Eicher <seiji@anyscale.com> Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
Seiji Eicher committed
Feb 11, 2026 at 02:25 UTC
5045d5c9831a3a4a423a409ccea521d299a43a9a
2 files changed
+2
-2
requirements/build.txt
+1
-1
@@ -9,5 +9,5 @@ wheel
9
jinja2>=3.1.6
10
regex
11
build
12
-protobuf
12
+protobuf >= 5.29.6, !=6.30.*, !=6.31.*, !=6.32.*, !=6.33.0.*, !=6.33.1.*, !=6.33.2.*, !=6.33.3.*, !=6.33.4.*
13
grpcio-tools==1.78.0 # Required for grpc entrypoints
requirements/common.txt
+1
-1
@@ -9,7 +9,7 @@ blake3
9
py-cpuinfo
10
transformers >= 4.56.0, < 5
11
tokenizers >= 0.21.1 # Required for fast incremental detokenization.
12
-protobuf # Required by LlamaTokenizer, gRPC.
12
+protobuf >= 5.29.6, !=6.30.*, !=6.31.*, !=6.32.*, !=6.33.0.*, !=6.33.1.*, !=6.33.2.*, !=6.33.3.*, !=6.33.4.* # Required by LlamaTokenizer, gRPC. CVE-2026-0994
13
fastapi[standard] >= 0.115.0 # Required by FastAPI's form models in the OpenAI API server's audio transcriptions endpoint.
14
aiohttp >= 3.13.3
15
openai >= 1.99.1 # For Responses API with reasoning content