CVE-2026-105755
vLLM is an inference and serving engine for large language models. …
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can overwrite the cached query embedding so the victim's documents are scored against the attacker's query, and shared use counters can also cause a late-interaction cache-miss error. This issue is fixed in version 0.30.0.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/vllm-project/vllm/commit/ee17d0d869203ef9a35ad73358a4987bba14b1fc
- github.com/vllm-project/vllm/pull/51445
- github.com/vllm-project/vllm/releases/tag/v0.30.0
- github.com/vllm-project/vllm/security/advisories/GHSA-2phq-3phc-84px
- github.com/advisories/GHSA-2phq-3phc-84px
- nvd.nist.gov/vuln/detail/CVE-2026-105755
- cve.org/CVERecord?id=CVE-2026-105755
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.