Lookup for vulnerabilities affecting packages.
| Vulnerability_id | VCID-jzjy-kj6h-4bas |
| Summary | vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0. |
| Aliases |
| 0 |
|
| 1 |
| alias |
GHSA-83vm-p52w-f9pw |
|
| 2 |
|
|
| Fixed_packages |
|
| Affected_packages |
|
| References |
|
| Weaknesses |
|
| Exploits |
|
| Severity_range_score | 6.5 - 6.5 |
| Exploitability | null |
| Weighted_severity | null |
| Risk_score | null |
| Resource_url | http://public2.vulnerablecode.io/vulnerabilities/VCID-jzjy-kj6h-4bas |