CVE-2026-55514
2 advisories.
PyPI/vllm CVE-2026-55514: high, EPSS 0.66%
vLLM denial of service via prompt embeds on M-RoPE models
Action: Upgrade vllm to 0.24.0 or later.
pip install vllm==0.24.0Affected
| introduced | fixed | last affected |
|---|---|---|
| 0.12.0 | 0.24.0 | - |
Fixed versions
| 0.24.0 |
Sources
- osv: GHSA-33cg-gxv8-3p8g
- https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g
- https://nvd.nist.gov/vuln/detail/CVE-2026-55514
- https://github.com/vllm-project/vllm/pull/45252
- https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65
- https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2303.yaml
- https://github.com/vllm-project/vllm
- https://github.com/vllm-project/vllm/releases/tag/v0.24.0
CVE-2026-55514 · published · modified · JSON
PyPI/vllm CVE-2026-55514: medium 6.5, EPSS 0.66%
vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an
Action: Upgrade vllm to 0.24.0 or later.
pip install vllm==0.24.0Affected
| introduced | fixed | last affected |
|---|---|---|
| 0.12.0 | 0.24.0 | - |
Fixed versions
| 0.24.0 |
Sources
- osv: PYSEC-2026-2303
- https://github.com/vllm-project/vllm/releases/tag/v0.24.0
- https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g
- https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65
- https://github.com/vllm-project/vllm/pull/45252
CVE-2026-55514 · published · modified · JSON