CyberSecBulletin
CVE-2026-94627NVD status: Analyzed

vllm: Missing Release of Memory after Effective Lifetime

Published Updated By the CyberSecBulletin desk

CVE-2026-94627 is a high-severity missing release of memory after effective lifetime vulnerability in vllm from Vllm-project, with a CVSS 3.1 base score of 7.5 out of 10. It can be exploited remotely over the network by an unauthenticated attacker, without any action from a user. Affected vllm versions: 0.29.0 and earlier. The record does not name a fixed version, so check the vendor advisory. There is no confirmed exploitation so far. EPSS estimates a 0.63% chance of exploitation within 30 days, higher than 51% of scored CVEs.

Next patch cycle

High severity with no evidence of exploitation so far.

What to do

  1. Check which version of vllm you run against the affected versions below, and install the vendor's latest release.
  2. Until you can update, restrict network access to the affected service so it is not reachable from untrusted networks.

Affected products and versions

VendorProductAffected versionsFixed in
Vllm-projectvllm0.29.0 and earlierNot stated

Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.

How the severity score breaks down

Attack vector
NetworkCan be exploited remotely over a network, including the internet.
Attack complexity
LowNo special conditions are needed; the attack works reliably.
Privileges required
NoneNo account or login is needed.
User interaction
NoneNo action by a victim is required.
Scope
UnchangedImpact stays within the vulnerable component.
Confidentiality
NoneNo data is disclosed.
Integrity
NoneNothing can be modified.
Availability
HighThe component can be taken down completely.

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H. Scored by CNA (vulncheck.com).

Scoring systemScoreSeverityScored by
CVSS 4.08.7HighCNA (vulncheck.com)
CVSS 3.17.5HighCNA (vulncheck.com)

Official description

vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Attackers can trigger GPU memory exhaustion by submitting completion requests with multiple prompts, causing orphaned KV cache blocks to accumulate until process restart and eventually preventing legitimate requests from executing.

Source: the CVE record as published by its numbering authority, via NVD and CVE.org.

The underlying weakness: Missing Release of Memory after Effective Lifetime

The product does not sufficiently track and release allocated memory after it has been used, making the memory unavailable for reallocation and reuse.

How developers prevent this class of flaw

  • Choose a language or tool that provides automatic memory management, or makes manual memory management less error-prone. For example, glibc in Linux provides protection against free of invalid pointers. When using Xcode to target OS X or iOS, enable automatic reference counting (ARC). To help correctly and consistently manage memory when programming in C++, consider using a smart pointer class such as std
  • Use an abstraction library to abstract away risky APIs. Not a complete solution.
  • Consider using the Boehm-Demers-Weiser garbage collector (bdwgc), which can help avoid leaks.

More Missing Release of Memory after Effective Lifetime vulnerabilities (CWE-401)

Timeline

  1. CVE record published.
  2. CISA published its SSVC assessment (exploitation: none, automatable: yes, technical impact: partial).
  3. Record last changed materially (score, affected products, status or references).

References

Patches and release notes

Other vulnerabilities in vllm

All vllm vulnerabilities

Recent Missing Release of Memory after Effective Lifetime vulnerabilities

Spotted an error? Tell us.