Advisory details:
pypa / vllm/PYSEC-2026-4347
| Advisory ID | pypa/vllm/PYSEC-2026-4347 |
| Aliases |
CVE-2026-115916
GHSA-q97c-p368-75c4 PYSEC-2026-4347 |
| Summary | vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0. |
| Status | Published |
| Exploitability | 0.5 |
| Weighted Severity | 5.9 |
| Risk | 3.0 |
| Affected and Fixed Packages | Package Details |
| Introduced and Fixed Package Commit Patches | Package Commit Patches Details |
| There are no known CWE. |
| System | Score | Found at |
|---|---|---|
| cvssv3.1 | 6.5 | https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-4347.yaml |
No EPSS data available for this advisory.
| Patch URL | |
|---|---|
| There are no known patches. | |
| Attack Vector (AV) | Attack Complexity (AC) | Privileges Required (PR) | User Interaction (UI) | Scope (S) | Confidentiality Impact (C) | Integrity Impact (I) | Availability Impact (A) |
|---|---|---|---|---|---|---|---|
network adjacent_network local physical |
low high |
none low high |
none required |
unchanged changed |
high low none |
high low none |
high low none |
There are no SSVC decisions available.