{"id":"CVE-2026-54235","aliases":["EUVD-2026-38402","GHSA-7h4p-rffg-7823","PYSEC-2026-3405"],"status":"published","title":"vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels","description":"vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll 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. This vulnerability is fixed in 0.23.1rc0.","severity":{"version":"4.0","score":6.9,"vector":"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","level":"medium","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-11","score":0.0045,"percentile":0.39559,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-1287"],"published":"2026-06-17T14:02:22Z","modified":"2026-10-28T02:31:04Z","fixes":[{"ecosystem":"PyPI","package":"vllm","fixed_in":["0.24.0"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.8.5"},{"last_affected":"0.23.0"},{"fixed":"0.24.0"}]}]},{"source":"osv","ecosystem":"PyPI","package":"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"]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"0.23.0"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","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","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.20.0","0.20.1","0.20.2","0.21.0","0.22.0","0.22.1","0.23.0","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1","0.5.1","0.5.2","0.5.3","0.5.3.post1","0.5.4","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"]}],"products":[{"vendor":"vllm","product":"vllm"},{"vendor":"vllm-project","product":"vllm"}],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823","tags":["x_refsource_CONFIRM","Exploit","Third Party Advisory","advisory","web"]},{"url":"https://github.com/vllm-project/vllm/pull/45116","tags":["x_refsource_MISC","Issue Tracking","fix","web"]},{"url":"https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198","tags":["x_refsource_MISC","Patch","fix","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-54235","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-7h4p-rffg-7823","tags":["advisory"]},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-3405.yaml","tags":["web"]},{"url":"https://github.com/vllm-project/vllm","tags":["package"]},{"url":"https://pypi.org/project/vllm","tags":["web","package"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/54xxx/CVE-2026-54235.json","tags":["advisory"]}],"sources":{"cve":[{"id":"CVE-2026-54235","title":"vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels","description":"vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll 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. This vulnerability is fixed in 0.23.1rc0.","status":"published","published":"2026-06-22T21:59:02.71Z","modified":"2026-06-23T12:26:01.329Z","cvss":[{"version":"4.0","score":6.9,"vector":"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","level":"medium","assessor":"cna"}],"cwes":["CWE-1287"],"updated_at":"2026-11-02T13:38:09.774038Z"}],"euvd":[{"id":"EUVD-2026-38402","description":"vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll 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. This vulnerability is fixed in 0.23.1rc0.","status":"published","published":"2026-06-22T21:59:02Z","modified":"2026-06-23T12:26:01Z","cvss":[{"version":"4.0","score":6.9,"vector":"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","level":"medium"}],"updated_at":"2026-11-02T18:20:33.850201Z"}],"ghsa":[{"id":"GHSA-7h4p-rffg-7823","title":"vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels","description":"## 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","status":"published","published":"2026-06-17T14:02:22Z","modified":"2026-07-17T16:40:01Z","cvss":[{"version":"4.0","score":6.9,"vector":"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","level":"medium"},{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L","level":"medium"}],"cwes":["CWE-1287"],"updated_at":"2026-11-02T14:40:44.915484Z"}],"nvd":[{"id":"CVE-2026-54235","description":"vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll 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. This vulnerability is fixed in 0.23.1rc0.","status":"published","published":"2026-06-22T23:16:31.143Z","modified":"2026-10-25T23:10:00.167Z","cvss":[{"version":"4.0","score":6.9,"vector":"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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","level":"medium","assessor":"secondary"},{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L","level":"medium","assessor":"primary"}],"cwes":["CWE-1287"],"updated_at":"2026-11-02T14:12:25.288279Z"}],"osv":[{"id":"CVE-2026-54235","title":"vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels","description":"vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll 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. This vulnerability is fixed in 0.23.1rc0.","status":"published","published":"2026-06-22T21:59:02.71Z","modified":"2026-10-28T02:31:04.868068176Z","cvss":[{"version":"4.0","score":6.9,"vector":"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","level":"medium"}],"cwes":["CWE-1287"],"updated_at":"2026-11-02T15:45:10.818486Z"},{"id":"GHSA-7h4p-rffg-7823","title":"vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels","description":"## 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","status":"published","published":"2026-06-17T14:02:22Z","modified":"2026-09-10T03:50:48.693939195Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L","level":"medium"},{"version":"4.0","score":6.9,"vector":"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","level":"medium"}],"cwes":["CWE-1287"],"updated_at":"2026-11-02T15:46:41.002603Z"},{"id":"PYSEC-2026-3405","title":"vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels","description":"## 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","status":"published","published":"2026-07-13T15:46:18.517395Z","modified":"2026-07-13T16:33:32.259393907Z","cvss":[{"version":"4.0","score":6.9,"vector":"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","level":"medium"}],"updated_at":"2026-11-02T15:52:56.847083Z"}]}}