CVE-2026-115913 json
vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine
published 2026-10-26 13 d ago modified 2026-11-02 6 d ago also GHSA-8397-8qf6-f2gm , EUVD-2026-110023
- cvss
- 6.5
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.3%
- EPSS 0.3% chance of exploitation in 30 days, percentile 26%
- public exploits
- 0
- none known
Summary
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the Phi-4 multimodal audio encoder in phi4mm_audio.py and phi4mm_utils.py uses eager attention by default, allowing a remote client to submit one legal long audio clip that causes MultiHeadedAttention.forward_attention to materialize and retain full attention matrices in self.attn. The scaled dot-product attention branch does not materialize these matrices. The resulting quadratic GPU-memory use can cause an out-of-memory condition and terminate EngineCore for all users. This issue is fixed in version 0.32.0.
Patch / fix
- pypi vllm 0.32.0
- vllm vllm 0.32.0
CISA SSVC
- Exploitation
- none
- Automatable
- no
- Technical impact
- partial
- Assessed
- 6 d ago
Exploit prediction
0.33% chance of exploitation in the next 30 days, higher than 26% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 6.5 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |
| GitHub | 3.1 | 6.5 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | vllm | <0.32.0 |
0.32.0 |
Affected products
- vllm-project vllm
Classification
- Weakness
-
- CWE-770 Allocation of Resources Without Limits or Throttling
References
-
github.com
/vllm-project/vllm/pull/60614
web, patch
-
github.com
/vllm-project/vllm/commit/3d52578e13454de0bb8352cac988347cdcc89928
web, patch
-
github.com
/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm
web, exploit, patch, vendor-advisory
-
github.com
/vllm-project/vllm/releases/tag/v0.32.0
web, release-notes
-
nvd.nist.gov
/vuln/detail/CVE-2026-115913
advisory
-
github.com
/vllm-project/vllm
package
Sources
- CVE List CVE-2026-115913
- GitHub Advisory GHSA-8397-8qf6-f2gm
- NVD CVE-2026-115913
Fencer Vulns 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.