Every CVE Search/ Get API key

CVE-2026-93841

vLLM through 0.29.0 Adjacent-Request Sampler State Corruption via Unvalidated Prompt Token IDs

6.3 MediumFix available

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.

Attack profile

How easy it is to exploit

Attack vector
Network
Complexity
Low
Privileges needed
None
User interaction
None

What an attacker can affect

Confidentiality
None
Integrity
Low
Availability
None

Exploit likelihood

0.24%Unchanged since Sep 19, 2026
90%50%10%1%

What each source reports

CVE List Score used 6.3

vLLM through 0.29.0 Adjacent-Request Sampler State Corruption via Unvalidated Prompt Token IDs

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.

Record
CVE-2026-93841
CVSS 4.0
6.3 MediumCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N
CVSS 3.1
3.7 LowCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N
Weakness
CWE-129
Updated
2026-11-02
EUVDEUVD-2026-83285 6.3

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.

Record
EUVD-2026-83285
CVSS 4.0
6.3 MediumCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N
Updated
2026-11-02
GitHub AdvisoriesGHSA-q9hm-g73w-q6wp 6.3

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel...

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.

Record
GHSA-q9hm-g73w-q6wp
CVSS 4.0
6.3 MediumCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
CVSS 3.1
3.7 LowCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N
Weakness
CWE-129
Updated
2026-11-02
NVD 6.3

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.

Record
CVE-2026-93841
CVSS 4.0
6.3 MediumCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
CVSS 3.1
3.7 LowCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N
CVSS 3.1
5.3 MediumCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N
Weakness
CWE-129
Updated
2026-11-02
OSV 6.3

vLLM through 0.29.0 Adjacent-Request Sampler State Corruption via Unvalidated Prompt Token IDs

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.

Record
CVE-2026-93841
CVSS 4.0
6.3 MediumCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N
Weakness
CWE-129
Updated
2026-11-02
OSVPYSEC-2026-3999 5.3

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.

Record
PYSEC-2026-3999
CVSS 3.1
5.3 MediumCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N
Updated
2026-11-02
OSVopenSUSE-SU-2026:11867-1 No score

python313-vllm-0.30.0-1.1 on GA media

These are all security issues fixed in the python313-vllm-0.30.0-1.1 package on the GA media of openSUSE Tumbleweed.

Record
openSUSE-SU-2026:11867-1
Updated
2026-11-02

Affected products

Affected packages

Affected packages
PackageAffectedFixed
vllm
PyPI
before 0.30.0, plus listed versions
0.0.10.1.00.1.10.1.20.1.3
Show 45 moreShow less
0.1.40.1.50.1.60.1.70.10.00.10.10.10.1.10.10.20.11.00.11.10.11.20.12.00.13.00.14.00.14.10.15.00.15.10.16.00.17.00.17.10.18.00.18.10.19.00.19.10.2.00.2.10.2.1.post10.2.20.2.30.2.40.2.50.2.60.2.70.20.00.20.10.20.20.21.00.22.00.22.10.23.00.24.00.25.00.25.10.26.00.27.0
0.30.0
python-vllm
openSUSE:Tumbleweed
From an advisory covering 4 CVEs
before 0.30.0-1.1
0.30.0-1.1

History

History
RecordedChangedSources
affected, facts
first indexedCVE List, EUVD, GitHub Advisories, NVD, OSV

Dates are when Every CVE recorded each change. Upstream dates may differ.

In short

CVE-2026-93841 is a medium vulnerability (CVSS 6.3) in Vllm, published September 18, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.24%, the 14th percentile. Fixed in vllm 0.30.0.

References

Show 5 moreShow less
This page doesn't list everything

Left out here: 47 versions. The JSON record has them.

MoveEnter Open