vLLMGHSA-w2r7-9579-27hf
vLLM denial of service vulnerability
High7.5CVE-2024-8768 · Published Sep 17, 2024 · updated Aug 7, 2026
Affected versions
| Package | Affected | Fixed in |
|---|---|---|
| vllm PyPI | < 0.5.5 | 0.5.5 |
Details and references
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.
- 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| Date | Advisory | Severity | Fixed in |
|---|---|---|---|
| Sep 172024 | vLLM Denial of Service via the best_of parameter CVE-2024-8939Medium6.2no fix yet | Medium6.2 | No fix yet |
| Jan 272025 | vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator CVE-2025-24357High7.5fixed in 0.7.0 | High7.5 | 0.7.0 |
| Feb 62025 | vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache CVE-2025-25183Low2.6fixed in 0.7.2 | Low2.6 | 0.7.2 |
| Mar 192025 | vLLM denial of service via outlines unbounded cache on disk CVE-2025-29770Medium6.5fixed in 0.8.0 | Medium6.5 | 0.8.0 |
| Mar 192025 | vLLM Allows Remote Code Execution via Mooncake Integration CVE-2025-29783Critical9.0fixed in 0.8.0 | Critical9.0 | 0.8.0 |
| Mar 202025 | vLLM Deserialization of Untrusted Data vulnerability CVE-2024-11041Critical9.8no fix yet | Critical9.8 | No fix yet |