{"id":"GHSA-7h4p-rffg-7823","summary":"vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels","details":"## Summary\n\nAll temperature validation gates use comparison operators (`\u003c`, `\u003e`), which silently evaluate to `False` for `NaN` and for positive `Infinity` in Python's IEEE 754 float semantics. Both values pass every guard and propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors that can crash the inference worker. Note: `-Infinity` is correctly caught.\n\n## Root Cause\n\n`sampling_params.py:384`:\n```python\nif 0 \u003c self.temperature \u003c _MAX_TEMP:  # NaN → False; +Inf → False\n```\n\n`sampling_params.py:462`:\n```python\nif self.temperature \u003c 0.0:            # NaN → False; +Inf → False\n    raise VLLMValidationError(...)\n```\n\nNo `math.isnan()` or `math.isinf()` check exists anywhere in `sampling_params.py`.\n\nPython semantics (verified): `float('nan') \u003c 0.0` → `False`, `float('inf') \u003c 0.0` → `False`.\n\n\n## Impact\n\nCrash of inference worker on GPU kernel execution with NaN/Inf softmax input, degrading service for all concurrent users.\n\n## Remediation\n\nAdd `math.isfinite(self.temperature)` check in `_verify_args()`. Reject non-finite float values with a 400 error.\n\n## Fix\n\nA fix for this vulnerability was merged here: https://github.com/vllm-project/vllm/pull/45116","aliases":["CVE-2026-54235","PYSEC-2026-3405"],"modified":"2026-09-10T03:50:48.693939195Z","published":"2026-06-17T14:02:22Z","database_specific":{"nvd_published_at":"2026-06-22T23:16:31Z","cwe_ids":["CWE-1287"],"severity":"MODERATE","github_reviewed":true,"github_reviewed_at":"2026-06-17T14:02:22Z"},"references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-54235"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/45116"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198"},{"type":"ADVISORY","url":"https://github.com/advisories/GHSA-7h4p-rffg-7823"},{"type":"WEB","url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-3405.yaml"},{"type":"PACKAGE","url":"https://github.com/vllm-project/vllm"},{"type":"WEB","url":"https://pypi.org/project/vllm"}],"affected":[{"package":{"name":"vllm","ecosystem":"PyPI","purl":"pkg:pypi/vllm"},"ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.8.5"},{"fixed":"0.24.0"}]}],"versions":["0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.11.1","0.11.2","0.12.0","0.13.0","0.14.0","0.14.1","0.15.0","0.15.1","0.16.0","0.17.0","0.17.1","0.18.0","0.18.1","0.19.0","0.19.1","0.20.0","0.20.1","0.20.2","0.21.0","0.22.0","0.22.1","0.23.0","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"],"database_specific":{"source":"https://github.com/github/advisory-database/blob/main/advisories/github-reviewed/2026/06/GHSA-7h4p-rffg-7823/GHSA-7h4p-rffg-7823.json","last_known_affected_version_range":"\u003c= 0.23.0"}}],"schema_version":"1.9.0","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L"},{"type":"CVSS_V4","score":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N"}]}