Answer in brief
CVE-2026-33625 records a High severity (CVSS 8.8) vulnerability in LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading. The current sources do not mark it as known exploited. The current feed maps InternLM/lmdeploy (generic), lmdeploy (pip). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 8.8. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps InternLM/lmdeploy (generic), lmdeploy (pip). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| InternLM/lmdeploygeneric | >= 0.12.1, < 0.12.3 | Not reported |
| lmdeploypip | >=0.12.1,<0.12.3 | 0.12.3 |
Published upstream
Sep 18, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Sep 18, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Sep 18, 2026
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.
Quoted source text, attributed separately from HOL analysis.