All vulnerabilities

Servers and applications

CVE-2026-105753

Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core

Severity
Medium 6.5
Published
28 Sept 2026
Last changed
8 Oct 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.28.0
Exploit chance
0.4% in the next 30 daysHigher than 37% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
CWE-617
Attack
Over the network · Needs a user account · No user action needed
Attacker can
Take it down
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Also known as
GHSA-ph3r-5jfg-f84f
Sources
NVD, CVE Program, Project advisories (GitHub)

Description

vLLM's default multimodal cache (mm_processor_cache_type="lru") mirrors state across two processes: the frontend (P0) holds only metadata (MultiModalProcessorSenderCache) while the engine core (P1) holds the real payload (MultiModalReceiverCache). The design invariant is that get_and_update() runs on P0 and P1 in lockstep for every request, so eviction order stays mirrored and P0 can answer "is this cached in P1?" without talking to P1.

That invariant breaks when a request is rejected after P0 has rendered and hashed the multimodal input (populating the P0 cache) but before P1 receives the item — for example, an oversized chat prompt rejected on max_model_len after rendering. P0 now believes the media is cached while P1 never got it. A later request reusing the same media hash gets a P0 hit, so P0 sends None instead of the payload, and P1 — which has nothing cached — trips assert mm_item is not None, f"Expected a cached item for {mm_hash=}".

From vllm-project/vllm's security advisory. Shortened; the full text is there.

Affected software

SoftwareAffected versions
vLLMServers and applications · cna:vllm-project|vllm
  • Every version before 0.28.0
vLLMServers and applications · cpe:a:vllm:vllm
  • Every version before 0.28.0
vLLMServers and applications · github:vllm-project/vllm
  • Every version before 0.28.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
Docker Hub pulls
44,195,225Docker Hub, 15 Nov 2026
GitHub stars
96,943GitHub, 15 Nov 2026
Forks
24,836GitHub, 15 Nov 2026
Latest release
v0.33.0rc3GitHub, 15 Nov 2026
Released
2 Nov 2026GitHub
License
Apache Software License 2.0Wikidata
First published on GitHub
9 Feb 2023GitHub

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-105753
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-105753
  • GitHub Advisory Database https://github.com/advisories/GHSA-ph3r-5jfg-f84f
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84f