CVE-2026-105753
2 advisories.
PyPI/vllm CVE-2026-105753: medium 6.5
vLLM: 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
Action: Upgrade vllm to 0.28.0 or later.
pip install vllm==0.28.0Affected
| introduced | fixed | last affected |
|---|---|---|
| 0 | 0.28.0 | - |
Fixed versions
| 0.28.0 |
Sources
- osv: GHSA-ph3r-5jfg-f84f
- https://github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84f
- https://github.com/vllm-project/vllm/pull/46747
- https://github.com/vllm-project/vllm/pull/51897
- https://github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b8fa30190d26a9
- https://github.com/vllm-project/vllm
- https://github.com/vllm-project/vllm/releases/tag/v0.28.0
CVE-2026-105753 · published · modified · JSON
PyPI/vllm CVE-2026-105753: medium 6.5
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a media hash in the frontend sender cache during multimodal ren
Action: Upgrade vllm to 0.28.0 or later.
pip install vllm==0.28.0Affected
| introduced | fixed | last affected |
|---|---|---|
| 0 | 0.28.0 | - |
Fixed versions
| 0.28.0 |
Sources
- osv: PYSEC-2026-4197
- https://github.com/vllm-project/vllm/releases/tag/v0.28.0
- https://github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84f
- https://github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b8fa30190d26a9
- https://github.com/vllm-project/vllm/pull/46747
- https://github.com/vllm-project/vllm/pull/51897
CVE-2026-105753 · published · modified · JSON