vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
Published 6 Feb 2025 · Updated 7 Aug 2026
Is your project on an affected vllm?
Look after several Python apps? Indie watches up to 15 repos, private ones too, for $5 a month. See Indie
Affected package
- Affected
- <0.7.2
- Fixed in
- 0.7.2
pip install 'vllm>=0.7.2'Details
Summary
Maliciously constructed prompts can lead to hash collisions, resulting in prefix cache reuse, which can interfere with subsequent responses and cause unintended behavior.
Details
vLLM's prefix caching makes use of Python's built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable constant value. This makes it more feasible that someone could try exploit hash collisions.
Impact
The impact of a collision would be using cache that was generated using different content. Given knowledge of prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use.
Solution
We address this problem by initializing hashes in vllm with a value that is no longer constant and predictable. It will be different each time vllm runs. This restores behavior we got in Python versions prior to 3.12.
Using a hashing algorithm that is less prone to collision (like sha256, for example) would be the best way to avoid the possibility of a collision. However, it would have an impact to both performance and memory footprint. Hash collisions may still occur, though they are no longer straight forward to predict.
To give an idea of the likelihood of a collision, for randomly generated hash values (assuming the hash generation built into Python is uniformly distributed), with a cache capacity of 50,000 messages and an average prompt length of 300, a collision will occur on average once every 1 trillion requests.
References
- https://github.com/vllm-project/vllm/pull/12621
- https://github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7
- https://github.com/python/cpython/pull/99541
Is GHSA-rm76-4mrf-v9r8 in any of your client repos?
Checking one package by hand is fine. Checking it across forty client projects is not. NPMscan reads the lockfiles in every GitHub repo you pick, finds each project with an affected vllm, and gives you the command that fixes it.
More advisories for vllm
- LowCVE-2026-115917vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server · 28 Oct 2026
- MediumCVE-2026-115913vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine · 28 Oct 2026
- MediumCVE-2026-115914vLLM DeepSeek-OCR image processing vulnerable to denial of service · 28 Oct 2026
- HighCVE-2026-115915vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE · 28 Oct 2026
- HighCVE-2026-115912vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled · 28 Oct 2026
- MediumCVE-2026-115916vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS) · 28 Oct 2026
References
- Linkgithub.com/vllm-project/vllm/security/advisories/GHSA-rm76-4mrf-v9r8
- Advisorynvd.nist.gov/vuln/detail/CVE-2025-25183
- Linkgithub.com/python/cpython/pull/99541
- Linkgithub.com/vllm-project/vllm/pull/12621
- Linkgithub.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7
- Linkgithub.com/vllm-project/vllm/commit/73b35cca7f3745d07d439c197768b25d88b6ab7f
- Linkgithub.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-62.yaml
- Packagegithub.com/vllm-project/vllm
Advisory data from OSV.dev (opens OSV.dev in a new tab), refreshed daily.