Read the docs

Resource exhaustion in vLLM via request-level num_frames

Priority LOW 31CWE-770Published · Updated

Key facts

Attack vector
Network
Privileges required
Low
User interaction
None
Attack complexity
Low
Attack requirements
None
Impact type
Denial of service
Confidentiality · integrity · availability
None · None · High
Fix status
Fixed

Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-770.

Summary

vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion flaw that lets inference clients bypass the server frame limit by setting media_io_kwargs.video.num_frames in chat completion requests. An authenticated remote attacker with low privileges can send a request with num_frames set to -1 or a large value along with many base64 JPEG frames, which forces the server to decode and stack all frames in memory and exhausts available memory (CWE-770).

Written with Claude Haiku 5.5 from the sources below · 2026-11-13

Description from the CNA

vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion vulnerability that allows inference clients to bypass the server frame limit by setting media_io_kwargs.video.num_frames in chat completion requests. Attackers can supply num_frames=-1 or a large value with many base64 JPEG frames, forcing VideoMediaIO to decode all frames and np.stack them, causing memory exhaustion.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00409 35th percentileScored 2026-11-16
Fix Fixed vllm (vllm-project): 0.31.0

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
vllm-projectvllm0.19.0 to before 0.31.00.31.0Patch availableCNA
  • vllm Vendorvllm-project Affected 0.19.0 to before 0.31.0 Fixed in 0.31.0 Patch available CNA

CPE names Threatist (inferred) · 1

Inferred from how NVD named this product before; not given by a source.

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*——vLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions — — ·vLLM

Remediation

Upgrade vllm to version 0.31.0 or later, which fixes the flaw.

Written with Claude Haiku 5.5 from the sources below · 2026-11-13

  • Fix · CNA vllm (vllm-project) Fixed in 0.31.0

Fixed in the same release

Records fixed by the same vendor advisory or release, as the CNA lists them.

  • Release ·

    vllm-project vllm 0.31.0

    5 records Highest priority Priority LOW 5 LOW

    Other records, highest priority first

    • TI-2026-91290 vLLM Cohere2 Vision denial of service via max_patchesPriority LOW 38
    • TI-2026-91289 Resource exhaustion in vLLM MiniMax M3 via min_pixelsPriority LOW 37
    • TI-2026-91288 Information disclosure in vLLM sanitize_message() leaks heap addressesPriority LOW 36

Timeline

  1. 2026-11-13 Threatist record created from CVE-2026-126399
  2. 2026-11-13 Alias added: GHSA-gm8j-8578-p8q4
  3. 2026-11-13 CISA SSVC decision points changed

References

  • TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
  • TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
  • TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
  • TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
  • TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
  • TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5
See all 131 →

Sources