Service interruption via unbounded best_of processing
Published Sep 17, 2024 · Updated Nov 20, 2025
Resource exhaustion in vLLM before 0.5.0.post1 and RHEL AI allows attackers to make the JSON completion API unresponsive. The completion handler accepts best_of as the number of candidate generations without an effective bound or timeout, so a large value consumes excessive processing resources. Exposure beyond localhost is required, and exhaustion interrupts API service without reported data disclosure or modification.
Summary
What happened
Resource exhaustion in vLLM before 0.5.0.post1 and RHEL AI allows attackers to make the JSON completion API unresponsive. The completion handler accepts best_of as the number of candidate generations without an effective bound or timeout, so a large value consumes excessive processing resources. Exposure beyond localhost is required, and exhaustion interrupts API service without reported data disclosure or modification.
The record
- CVE
- CVE-2024-8939
- Published
- Sep 17, 2024
- Updated
- Nov 20, 2025
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- CWE-400, T1499.004
- Attack vector
- local
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 17, 2024CVE publishedPublication date reported by the CVE source.
- Nov 20, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <0.5.0.post1
What conditions does exploitation require?
What is affected?
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo