Disclosure summary
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.
Source-reported weakness categories
CWE-639
Source-specific records & product guidance
Sources retain their own attribution and scoring. Follow the original record to confirm affected versions, fixed releases, and configuration conditions.
NIST National Vulnerability Database · NVD-CVE-2026-105755
Open original source · Updated Oct 06, 2026
Only CPE matches marked vulnerable=true are indexed. AND/OR platform conditions must be checked in the original NVD record.
GitHub Reviewed Security Advisories · GHSA-2phq-3phc-84px
Open original source · Updated Oct 05, 2026
vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank`
Source severity: MEDIUM / 0
| Ecosystem | Package | Affected range | First patched |
|---|---|---|---|
| pip | vllm | < 0.30.0 | 0.30.0 |
Original records & references
PUBLISHED 2026-10-05T19:17:02-04:00
MODIFIED 2026-10-06T10:59:48-04:00
INGESTED 2026-10-06T11:45:40-04:00