Advisoriesby IbisvLLMGHSA-w2r7-9579-27hf
vLLM denial of service vulnerability
Fix: upgrade to 0.5.5 or later
A flaw was found in the vLLM library. A completions API request with an empty prompt will crash the vLLM API server, resulting in a denial of service.
Affected versions
| Package | Affected | Fixed in |
|---|---|---|
| vllm PyPI | < 0.5.5 | 0.5.5 |
Details and references
- CVSS 3.1
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Severity from
- GitHub (reviewed advisory)
- Weakness
- CWE-617
- Also known as
- CVE-2024-8768, PYSEC-2026-2024
- nvd.nist.gov/vuln/detail/CVE-2024-8768
- github.com/vllm-project/vllm/issues/7632
- github.com/vllm-project/vllm/pull/7746
- github.com/vllm-project/vllm/commit/e25fee57c2e69161bd261f5986dc5aeb198bbd42
- access.redhat.com/security/cve/CVE-2024-8768
- bugzilla.redhat.com/show_bug.cgi?id=2311895
- github.com/vllm-project/vllm
More vLLM advisories
All vLLM
vLLM Deserialization of Untrusted Data vulnerabilityCVE-2024-11041no fix yetvLLM Allows Remote Code Execution via Mooncake IntegrationCVE-2025-29783fixed in 0.8.0vLLM denial of service via outlines unbounded cache on diskCVE-2025-29770fixed in 0.8.0vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cacheCVE-2025-25183fixed in 0.7.2vllm: Malicious model to RCE by torch.load in hf_model_weights_iteratorCVE-2025-24357fixed in 0.7.0vLLM Denial of Service via the best_of parameterCVE-2024-8939no fix yet