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-2026-53923
vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving
Fixed in 0.24.0
High
7.5
Fix available
Jun 17
CVE-2026-12491
vLLM: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations
Fixed in 0.24.0
Medium
4.8
Fix available
Jun 17
CVE-2026-54235
vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels
Fixed in 0.24.0
Medium
6.5
Fix available
Jun 17
CVE-2026-48746
vLLM: OpenAI auth bypass
Fixed in 0.22.0
Critical
9.1
Fix available
Jun 16
CVE-2026-41523
vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution
Fixed in 0.22.0
High
7.5
Fix available
Jun 16
CVE-2026-5497
vLLM is vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method
Fixed in 0.19.0
High
7.5
Fix available
Jun 11
CVE-2026-47155
vLLM's Artifact Pin Decay allows pinned deployments to load unpinned code, weights, and processors
Fixed in 0.22.0
Medium
6.5
Fix available
Jun 10
CVE-2026-9540
vllm has Improper Resource Shutdown or Release
No fix yet
Medium
5.3
May 26
CVE-2026-44223
vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters
Fixed in 0.20.0
Medium
6.5
Fix available
May 6
CVE-2026-44222
vLLM Vulnerable to Remote DoS via Special-Token Placeholders
Fixed in 0.20.0
Medium
6.5
Fix available
May 5
CVE-2026-7141
vLLM makes Use of Uninitialized Resource
Fixed in 0.19.1
Medium
5.6
Fix available
Apr 27
CVE-2026-34755
vLLM: Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing
Fixed in 0.19.0
Medium
6.5
Fix available
Apr 3
CVE-2026-34753
vLLM: Server-Side Request Forgery (SSRF) in `download_bytes_from_url `
Fixed in 0.19.0
Medium
5.4
Fix available
Apr 3
CVE-2026-34756
vLLM: Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server
Fixed in 0.19.0
Medium
6.5
Fix available
Apr 3
CVE-2026-27893
vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out
Fixed in 0.18.0
High
8.8
Fix available
Mar 27
CVE-2026-25960
vLLM has SSRF Protection Bypass
Fixed in 0.17.0
Medium
5.4
Fix available
Mar 9
CVE-2026-22778
vLLM has RCE In Video Processing
Fixed in 0.14.1
Critical
9.8
Fix available
Feb 2
CVE-2026-24779
vLLM vulnerable to Server-Side Request Forgery (SSRF) through MediaConnector
Fixed in 0.14.1
High
7.1
Fix available
Jan 28
CVE-2026-22807
vLLM affected by RCE via auto_map dynamic module loading during model initialization
Fixed in 0.14.0
High
8.8
Fix available
Jan 21
CVE-2026-22773
vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions
Fixed in 0.12.0
Medium
6.5
Fix available
Jan 13
CVE-2026-56340
vLLM introduced enhanced protection for CVE-2025-62164
Fixed in 0.13.0
High
8.8
Fix available
Jan 8
CVE-2025-66448
vLLM vulnerable to remote code execution via transformers_utils/get_config
Fixed in 0.11.1
High
7.1
Fix available
Dec 2
CVE-2025-62426
vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`
Fixed in 0.11.1
Medium
6.5
Fix available
Nov 20
CVE-2025-62372
vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs
Fixed in 0.11.1
Medium
6.5
Fix available
Nov 20
CVE-2025-62164
vLLM deserialization vulnerability leading to DoS and potential RCE
Fixed in 0.11.1
High
8.8
Fix available
Nov 20
CVE-2025-6242
vLLM is vulnerable to Server-Side Request Forgery (SSRF) through `MediaConnector` class
Fixed in 0.11.0
High
7.1
Fix available
Oct 7
CVE-2025-61620
vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server
Fixed in 0.11.0
Medium
6.5
Fix available
Oct 7
CVE-2025-59425
vLLM is vulnerable to timing attack at bearer auth
Fixed in 0.11.0
High
7.5
Fix available
Oct 7
CVE-2025-9141
vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder
Fixed in 0.10.1.1
High
8.8
Fix available
Aug 21
CVE-2025-48956
vllm API endpoints vulnerable to Denial of Service Attacks
Fixed in 0.10.1.1
High
7.5
Fix available
Aug 21
Showing
61–90
of 113
Previous
1
2
3
4
Next