Skip to content
CVE
by OpenHack
Browse
All CVEs
Every CVE, newest first, with filters
CVEs by company
Microsoft, Cisco, Fortinet and 840 more
CVEs by package
Open-source packages on npm, PyPI, Maven, Go…
Critical
About
Search CVEs, products, packages and vendors
/
Packages
PyPI
vllm
vllm CVEs
PyPI package
Search CVEs, products, packages and vendors
Severity
Any
Published
All time
Exploited only
Version
113 CVEs
·
5 without a fix
·
CVE
Record
Severity
Status
Published
CVE-2025-48944
vLLM Tool Schema allows DoS via Malformed pattern and type Fields
Fixed in 0.9.0
Medium
6.5
Fix available
May 28
CVE-2025-48943
vLLM allows clients to crash the openai server with invalid regex
Fixed in 0.9.0
Medium
6.5
Fix available
May 28
CVE-2025-48942
vLLM DOS: Remotely kill vllm over http with invalid JSON schema
Fixed in 0.9.0
Medium
6.5
Fix available
May 28
CVE-2025-46722
vLLM has a Weakness in MultiModalHasher Image Hashing Implementation
Fixed in 0.9.0
Medium
4.2
Fix available
May 28
CVE-2025-46570
Potential Timing Side-Channel Vulnerability in vLLM’s Chunk-Based Prefix Caching
Fixed in 0.9.0
Low
2.6
Fix available
May 28
CVE-2025-71379
vLLM vulnerable to Regular Expression Denial of Service
Fixed in 0.9.0
Medium
4.3
Fix available
May 28
CVE-2025-48887
vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
Fixed in 0.9.0
Medium
6.5
Fix available
May 28
CVE-2025-47277
vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
Fixed in 0.8.5
Critical
9.8
Fix available
May 20
CVE-2025-30165
Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration
Fixed in 0.10.0
High
8.0
Fix available
May 6
CVE-2025-46560
vLLM: Quadratic Time Complexity in Input Token Processing leads to denial of service
Fixed in 0.8.5
Medium
6.5
Fix available
Apr 29
CVE-2025-32444
vLLM Vulnerable to Remote Code Execution via Mooncake Integration
Fixed in 0.8.5
Critical
10.0
Fix available
Apr 29
CVE-2025-30202
Data exposure via ZeroMQ on multi-node vLLM deployment
Fixed in 0.8.5
High
7.5
Fix available
Apr 29
GHSA-ggpf-24jw-3fcw
CVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0
Fixed in 0.8.0
Critical
9.8
Fix available
Apr 23
GHSA-hf3c-wxg2-49q9
vLLM vulnerable to Denial of Service by abusing xgrammar cache
Fixed in 0.8.4
Medium
6.5
Fix available
Apr 15
CVE-2024-9053
vLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypoints
No fix yet
Critical
9.8
Mar 20
CVE-2024-9052
vLLM deserialization vulnerability in vllm.distributed.GroupCoordinator.recv_object
No fix yet
Critical
9.8
Mar 20
CVE-2024-11041
vLLM Deserialization of Untrusted Data vulnerability
No fix yet
Critical
9.8
Mar 20
CVE-2025-29783
vLLM Allows Remote Code Execution via Mooncake Integration
Fixed in 0.8.0
Critical
9.0
Fix available
Mar 19
CVE-2025-29770
vLLM denial of service via outlines unbounded cache on disk
Fixed in 0.8.0
Medium
6.5
Fix available
Mar 19
CVE-2025-25183
vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
Fixed in 0.7.2
Low
2.6
Fix available
Feb 6
CVE-2025-24357
vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator
Fixed in 0.7.0
High
7.5
Fix available
Jan 27
CVE-2024-8768
vLLM denial of service vulnerability
Fixed in 0.5.5
High
7.5
Fix available
Sep 17
CVE-2024-8939
vLLM Denial of Service via the best_of parameter
No fix yet
Medium
6.2
Sep 17
Showing
91–113
of 113
Previous
1
2
3
4
Next