CVE-2026-105755 - 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`
CVE ID :CVE-2026-105755
Published : Oct. 5, 2026, 11:17 p.m. | 28 minutes ago
Description :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.
Severity: 4.2 | MEDIUM
Visit the link for more details, such as CVSS details, affected products, timeline, and more...
Published : Oct. 5, 2026, 11:17 p.m. | 28 minutes ago
Description :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.
Severity: 4.2 | MEDIUM
Visit the link for more details, such as CVSS details, affected products, timeline, and more...