Vllm

Vendor:

First CVE: Jan 27, 2025 · Active for 1 year

51
Total CVEs
Bottom 1%
25.5
Avg CVEs / Year
Bottom 1%
7.4
Avg CVSS
Higher Avg CVSS than 88% of tracked products
0.0%
KEV Rate
Bottom 1%

Trends Over Time

The number and severity of CVEs published that impact Vllm over time

Volume of CVEsAvg CVSS Base Score
First CVE
Jan 27, 2025
17 months ago
Most Recent CVE
Jul 6, 2026
22 days ago

CVE Severity & Scoring

Vllm51 CVEs
All CVEs353,240 CVEs
LowMediumHighCritical
Attack Vector
Local0 (0.0%)
Network49 (96.1%)
Unknown0 (0.0%)
Physical0 (0.0%)
Adjacent Network2 (3.9%)
Attack Complexity
Low46 (90.2%)
High5 (9.8%)
Unknown0 (0.0%)
User Interaction
None44 (86.3%)
Unknown0 (0.0%)
Required7 (13.7%)
Privileges Required
Low22 (43.1%)
High0 (0.0%)
None29 (56.9%)
Unknown0 (0.0%)

Top CVEs

Signals from CVEs in this product scope (51 CVEs).

51 CVEs · Highest risk first

CVEPublishedCVSSRiskKEVExploit
vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an er
Feb 2, 20269.853NOYES
vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in ASGI web servers and starlette's trust on those web servers en
Jun 22, 20269.139NONO
vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, a
Jun 20, 20268.837NONO
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules
Jan 21, 20269.837NONO
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitize_message helper that strips obj
Jun 22, 20265.335NOYES
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthent
Jun 22, 20267.534NONO
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is vulnerable to a dependency confusion attack through the flashinfer
Jun 22, 20268.834NONO
vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` me
Jun 11, 20267.534NONO
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular exp
Jul 6, 20267.533NONO
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the re
Jul 6, 20267.533NONO

Exploit Exposure

Signals from CVEs in this product scope (51 CVEs).

CISA KEV
0 CVEs
0.0% of CVEs· Bottom 1%
Metasploit
0 CVEs
0.0% of CVEs· Bottom 1%
Nuclei
2 CVEs
3.9% of CVEs· Bottom 1%
ExploitDB
0 CVEs
0.0% of CVEs· Bottom 1%

Social Chatter

Signals from CVEs in this product scope (51 CVEs).

Media Mentions

Signals from CVEs in this product scope (51 CVEs).

Top CNAs Publishing CVEs For Vllm

Top CWEs

Versions

VersionCVE CountAvg CVSSAvg EPSSKEVExploits
0.6.219.81.4%00
0.6.019.81.3%00
0.11.137.30.5%00
0.11.017.50.5%00