Skip to content
Fencer Intel
high 7.5

CVE-2026-54234 json

vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection

published 4mo ago modified 17d ago also GHSA-8wr5-jm2h-8r4f , PYSEC-2026-3542 , EUVD-2026-41921

cvss
7.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.6%
EPSS 0.6% chance of exploitation in 30 days, percentile 49%
public exploits
0
none known

Summary

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0.

Patch / fix

  • pypi vllm 0.24.0
  • vllm vllm 0.24.0

Is CVE-2026-54234 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-54234 updated cvss 7.5

vllm: vLLM: Denial of Service via malformed speculative decoding workload

  • Red Hat AI Inference Server rhaii/vllm-tpu-rhel9, rhaiis/vllm-cpu-rhel9, rhaiis/vllm-tpu-rhel9, rhaii/vllm-gaudi-rhel9, rhaii/vllm-neuron-rhel9, rhaiis/vllm-neuron-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-gaudi-rhel9
    affected: workaround, no fix planned “Will not fix”
  • Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-gaudi-rhel9
    affected: workaround, no fix available
  • Red Hat AI Inference Server 3.2 rhaiis/vllm-cuda-rhel9 1787860580, rhaiis/vllm-rocm-rhel9 1787884873
    fixed: vendor fix RHSA-2026:61627
  • Red Hat AI Inference Server 3.3 rhaiis/vllm-spyre-rhel9 1787161776
    fixed: vendor fix RHSA-2026:60363
  • Red Hat AI Inference Server 3.4 rhaii/vllm-cpu-rhel9 1789681128, rhaii/vllm-cpu-rhel9 1790075793, rhaii/vllm-cuda-rhel9 1789681126, rhaii/vllm-cuda-rhel9 1790090131, rhaii/vllm-rocm-rhel9 1789681126, rhaii/vllm-rocm-rhel9 1790109620, +2 more
    fixed: vendor fix RHSA-2026:69466
  • Red Hat Enterprise Linux AI 3.4 rhelai3/bootc-cuda-rhel9 1790868254, rhelai3/bootc-rocm-rhel9 1790614447, rhelai3/bootc-aws-cuda-rhel9 1790881122, rhelai3/bootc-gcp-cuda-rhel9 1790881123, rhelai3/disk-image-cuda-rhel9 1790957417, rhelai3/bootc-azure-cuda-rhel9 1790881120, +1 more
    fixed: vendor fix RHSA-2026:76150
  • Red Hat OpenShift AI (RHOAI) rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-llm-d-kv-cache-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-kserve-storage-initializer-rhel9
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
Proof of concept is public
Automatable
yes
Technical impact
partial
Assessed
4mo ago

Exploit prediction

0.62% chance of exploitation in the next 30 days, higher than 49% of all scored CVEs (FIRST EPSS, 2026-11-11).

Exploits and checks

  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
OSV 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
GitHub 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Affected packages

ecosystem package affected fixed in
pypi vllm
>=0.17.1, <0.24.0
0.24.0

Affected products

  • vllm-project vllm

Classification

Weakness
  • CWE-20 Improper Input Validation
  • CWE-1284 Improper Validation of Specified Quantity in Input

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.