CVE-2026-93436 vLLM through 0.29.0 Memory Exhaustion via Rejected Requests
Remote attackers can exhaust decode-worker memory by submitting rejected inference requests, causing denial of service in vLLM deployments.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-93436?
CVE-2026-93436 is a high-severity denial of service vulnerability in Vllm Vllm, published on 17 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requests with max_tokens=0 to exhaust decode-worker memory without bound until the worker restarts.
Weakness: CWE-401
Which versions are affected by CVE-2026-93436?
1 open source package ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | All versions | 0.30.0 |
Products include Vllm Vllm.
How do I fix CVE-2026-93436?
Upgrade vllm to 0.30.0 or later.
Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.
Is CVE-2026-93436 being exploited?
There is no known exploitation of CVE-2026-93436 in the wild and no public exploit code.
Other vulnerabilities in Vllm Vllm
- CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration
- CVE-2026-22778 vLLM leaks a heap address when PIL throws an error
- CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
- CVE-2024-11041 Remote Code Execution in vllm-project/vllm
- CVE-2026-48746 vLLM: OpenAI auth bypass
Sources
Also known as GHSA-jh5x-pggf-m4cr, MINI-6246-gx69-33w4, MINI-px87-mcvm-7rjv, MINI-wp6v-2m25-7qhc, PYSEC-2026-3996.