CVE-2026-93436PYSEC-2026-3996
vLLM through 0.29.0 Memory Exhaustion via Rejected Requests
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Fix
- Fixed in 0.30.0
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
CISA's decision points: whether it is exploited, whether attacks can be automated, and how much control an attacker gets. Assessed (SSVC 2.0.3).What do these mean? →
- Exploitation: none
- Automatable: yes
- Technical impact: partial
Summary
vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requests with max_tokens=0 to exhaust decode-worker memory without bound until the worker restarts.
Timeline
- CVE published
- CISA SSVC assessment
Exploitation: none · Automatable: yes · Technical impact: partial
- Record last updated
Affected versions
- vllm-project vllm
through 0.29.0
- vllmPyPI
fixed in 0.30.0