{"items":[{"id":"NVI-00016257","kind":"vulnerability","title":"vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-7h4p-rffg-7823","CVE-2026-54235"],"plain_summary":"GitHub lists this reviewed advisory for vllm. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-57d8007d950ef124bcaa6482ab08b738"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[{"kind":"CVSS","as_of":"2026-07-17T16:40:01.000Z","value":"6.5 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-57d8007d950ef124bcaa6482ab08b738"}],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-57d8007d950ef124bcaa6482ab08b738","url":"https://github.com/advisories/GHSA-7h4p-rffg-7823","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-7h4p-rffg-7823","publisher":"GitHub Advisory Database","observed_at":"2026-11-04T09:59:26.779Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-57d8007d950ef124bcaa6482ab08b738"],"technology":"vllm","known_exclusions":[],"conditions_summary":"## Summary\n\nAll temperature validation gates use comparison operators (``), 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 < self.temperature < _MAX_TEMP:  # NaN → False; +Inf → False\n```\n\n`sampling_params.py:462`:\n```python\nif self.temperature < 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') < 0.0` → `False`, `float('inf') < 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","public_affected_ranges":[">= 0.8.5, <= 0.23.0"]}],"null_published_at":"2026-11-04T10:04:27.924Z","source_updated_at":"2026-07-17T16:40:01.000Z","source_disclosed_at":"2026-06-17T14:02:22.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"First indexed by Null; source disclosure date is shown separately.","null_first_observed_at":"2026-11-04T09:59:26.779Z"}],"next_cursor":null,"snapshot_revision":"42594"}