## Summary All 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. ## Root Cause `sampling_params.py:384`: ```python if 0 < self.temperature < _MAX_TEMP: # NaN → False; +Inf → False ``` `sampling_params.py:462`: ```python if self.temperature < 0.0: # NaN → False; +Inf → False raise VLLMValidationError(...) ``` No `math.isnan()` or `math.isinf()` check exists anywhere in `sampling_params.py`. Python semantics (verified): `float('nan') < 0.0` → `False`, `float('inf') < 0.0` → `False`. ## Impact Crash of inference worker on GPU kernel execution with NaN/Inf softmax input, degrading service for all concurrent users. ## Remediation Add `math.isfinite(self.temperature)` check in `_verify_args()`. Reject non-finite float values with a 400 error. ## Fix A fix for this vulnerability was merged here: https://github.com/vllm-project/vllm/pull/45116
## Summary All 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. ## Root Cause `sampling_params.py:384`: ```python if 0 < self.temperature < _MAX_TEMP: # NaN → False; +Inf → False ``` `sampling_params.py:462`: ```python if self.temperature < 0.0: # NaN → False; +Inf → False raise VLLMValidationError(...) ``` No `math.isnan()` or `math.isinf()` check exists anywhere in `sampling_params.py`. Python semantics (verified): `float('nan') < 0.0` → `False`, `float('inf') < 0.0` → `False`. ## Impact Crash of inference worker on GPU kernel execution with NaN/Inf softmax input, degrading service for all concurrent users. ## Remediation Add `math.isfinite(self.temperature)` check in `_verify_args()`. Reject non-finite float values with a 400 error. ## Fix A fix for this vulnerability was merged here: https://github.com/vllm-project/vllm/pull/45116
Update vllm to 0.24.0 if you use the affected versions. Test the change in a non-production environment first.
Local check
hol-guard supply-chain scanvLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels affects vllm (pip), vllm (pip). Severity is medium. ## Summary All 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. ## Root Cause `sampling_params.py:384`: ```python if 0 < self.temperature < _MAX_TEMP: # NaN → False; +Inf → False ``` `sampling_params.py:462`: ```python if self.temperature < 0.0: # NaN → False; +Inf → False raise VLLMValidationError(...) ``` No `math.isnan()` or `math.isinf()` check exists anywhere in `sampling_params.py`. Python semantics (verified): `float('nan') < 0.0` → `False`, `float('inf') < 0.0` → `False`. ## Impact Crash of inference worker on GPU kernel execution with NaN/Inf softmax input, degrading service for all concurrent users. ## Remediation Add `math.isfinite(self.temperature)` check in `_verify_args()`. Reject non-finite float values with a 400 error. ## Fix A fix for this vulnerability was merged here: https://github.com/vllm-project/vllm/pull/45116
AI coding agents often install or upgrade packages automatically in pip. A medium vulnerability in a dependency can be pulled into a project through a normal install or update without a human reviewing the change, expanding the blast radius from a single package to every agent workspace that depends on it.
| Package | Affected range | Fixed version |
|---|---|---|
| vllmpip | <=0.23.0 | Not reported |
| vllmpip | >=0.8.5,<=0.23.0 | 0.24.0 |
Fixed versions are reported by the source feed; confirm compatibility before updating.
Reported by GitHub Security Advisories (ghsa).
HOL Guard can help your team review package activity against supported protection paths.
Explore HOL GuardUpdate vllm to 0.24.0 if you use the affected versions. Test the change in a non-production environment first.
Local check
hol-guard supply-chain scanvLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels affects vllm (pip), vllm (pip). Severity is medium. ## Summary All 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. ## Root Cause `sampling_params.py:384`: ```python if 0 < self.temperature < _MAX_TEMP: # NaN → False; +Inf → False ``` `sampling_params.py:462`: ```python if self.temperature < 0.0: # NaN → False; +Inf → False raise VLLMValidationError(...) ``` No `math.isnan()` or `math.isinf()` check exists anywhere in `sampling_params.py`. Python semantics (verified): `float('nan') < 0.0` → `False`, `float('inf') < 0.0` → `False`. ## Impact Crash of inference worker on GPU kernel execution with NaN/Inf softmax input, degrading service for all concurrent users. ## Remediation Add `math.isfinite(self.temperature)` check in `_verify_args()`. Reject non-finite float values with a 400 error. ## Fix A fix for this vulnerability was merged here: https://github.com/vllm-project/vllm/pull/45116
AI coding agents often install or upgrade packages automatically in pip. A medium vulnerability in a dependency can be pulled into a project through a normal install or update without a human reviewing the change, expanding the blast radius from a single package to every agent workspace that depends on it.
| Package | Affected range | Fixed version |
|---|---|---|
| vllmpip | <=0.23.0 | Not reported |
| vllmpip | >=0.8.5,<=0.23.0 | 0.24.0 |
Fixed versions are reported by the source feed; confirm compatibility before updating.
Reported by GitHub Security Advisories (ghsa).
HOL Guard can help your team review package activity against supported protection paths.
Explore HOL Guard