Resource exhaustion in Internlm Lmdeploy
CVE-2026-33625
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions 012.1 through 0.12.2 contain a code injection vulnerability in `lmdeploy/pytorch/config.py` line 620 that allows an attacker to execute arbitrary Python code by publishing a malicious HuggingFace model with a crafted `quantization_config.quant_dtype` value. When a user loads the model with lmdeploy, the `quant_dtype` is passed to `eval(f'torch.{quant_dtype}')` without any validation. Version 0.12.3 contains a patch.
Vulnerability class: DoS (Denial of Service)
CVSS v3 metric
CVSS v3 base score 8.8 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H.
Affected products
- Internlm Lmdeploy — versions >= 0.12.1, < 0.12.3
Weakness classification (CWE)
References
- security-advisories@github.com (x_refsource_CONFIRM)
- security-advisories@github.com (x_refsource_MISC)
Frequently asked questions
- What is CVE-2026-33625?
- CVE-2026-33625 is a high-severity vulnerability in Internlm Lmdeploy, classified under Uncontrolled Resource Consumption. CVSS score: 8.8/10. Published 2026-09-18.
- How severe is CVE-2026-33625?
- High severity. CVSS v3 base score is 8.8 out of 10.