CVE-2026-73559: vllm-project vllm Uncontrolled Resource Consumption
Vulnerability summary
CVE-2026-73559 is a medium (CVSS 6.5) Uncontrolled Resource Consumption vulnerability in vllm-project vllm. EPSS estimates a 0.58% chance of exploitation in the next 30 days, higher than 47.1% of scored vulnerabilities. 1 public exploit is recorded.
Advisory lineage
Upstream 0 · Downstream 0 · Related 1Timeline
- 13-08-2026PublishedVulnerability first disclosed.
- 14-08-2026Last modifiedVulnerability information updated.
Description
vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/inputs/preprocess.py and OnlineRenderer.preprocess_completion() in vllm/renderers/online_renderer.py expand every element, and vllm/entrypoints/openai/completion/serving.py creates one engine generator and response slot per prompt, allowing an authenticated API client to exhaust CPU, memory, async scheduling capacity, engine request slots, and response buffering with one request. This issue is fixed in version 0.26.0.
CVSS metrics
4 scores · 4 sources · 1 version- OSV · PypiEcosystem advisory · calculated6.5MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- OSV · ChainguardEcosystem advisory · calculated6.5MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- NVDNIST6.5MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EPSS trend
Probability
0.58%
Chance of exploitation in the next 30 days
Percentile
47%
Versus all other CVEs
30-day change
+0.11 pp
From 0.47% on 21-09-2026
Known exploited
Compare KEV catalogsNot in any of the 3 tracked catalogs.
Public exploits
1 foundVllm
Maturity: poc
Weaknesses
CWE · root causeAffected systems
Chainguard6 products
- kserve-huggingfaceserver-cuda-13.3All versions (No fix recorded)
- lmcache-cuda-12.8All versions (No fix recorded)
- nemo-rl-cuda-13.0-vllmAll versions (No fix recorded)
- tritonserver-backend-vllm-cuda-13.0< 25.11-r13
- vllm-openai-cuda-12.9< 0.28.0-r0
PyPI1 product
- vllm≥ 0.19.0, < 0.26.0
Vllm1 product
- vllm≥ 0.19.0, < 0.26.0
Vllm-project1 product
- vllm≥ 0.19.0, < 0.26.0
4 vendors · 9 products
References
9 links- github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756jX Refsource CONFIRMWEBAdvisoryExploitVendor Advisory
- github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569eX Refsource MISCWEBFIXPatch
- github.com/vllm-project/vllmPACKAGE
- pypi.org/project/vllmPACKAGE