Service exhaustion via duplicate transfer ID reuse
Published Sep 21, 2026 · Updated Sep 21, 2026
Resource exhaustion in the Mooncake connector in vLLM through 0.29.0 allows remote attackers to interrupt inference via crafted completion requests. Concurrent child requests sharing a transfer ID overwrite entries in the producer's reqs_need_send map, orphaning owned GPU KV-cache blocks. The flaw requires Mooncake prefill/decode disaggregation and multiple-prompt requests; accumulated blocks prevent legitimate inference until process restart.
Summary
What happened
Resource exhaustion in the Mooncake connector in vLLM through 0.29.0 allows remote attackers to interrupt inference via crafted completion requests. Concurrent child requests sharing a transfer ID overwrite entries in the producer's reqs_need_send map, orphaning owned GPU KV-cache blocks. The flaw requires Mooncake prefill/decode disaggregation and multiple-prompt requests; accumulated blocks prevent legitimate inference until process restart.
The record
- CVE
- CVE-2026-94627
- Published
- Sep 21, 2026
- Updated
- Sep 21, 2026
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- T1499.003
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 21, 2026CVE publishedPublication date reported by the CVE source.
- Sep 21, 2026Record 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 <=0.29.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
No CVSS assessment is available in this record.
CVSS describes severity. EPSS estimates exploitation probability.
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.
Activity data is delayed. The latest report is Sep 28, 2026.
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
Get started to see how Hinoki identifies affected software and validates exploitability in your environment.
Get started