CVE-2026-100647 vLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt
Unauthenticated attackers can cause denial of service in vLLM by sending oversized cache_salt values that stall the scheduler thread.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-100647?
CVE-2026-100647 is a medium-severity denial of service vulnerability in Vllm Vllm, published on 26 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP requests with multi-hundred-megabyte salt values that trigger expensive pickle serialization and SHA-256 hashing, stalling the scheduler thread and denying service to all concurrent requests.
Weakness: CWE-20
Which versions are affected by CVE-2026-100647?
It affects 1 product.
Products include Vllm Vllm.
How do I fix CVE-2026-100647?
Upgrade to a fixed version.
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-2026-100647 being exploited?
There is no known exploitation of CVE-2026-100647 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-hm89-h84f-px3x, GHSA-wpww-v874-ph2p, MINI-gg6v-m2h5-gppw, MINI-mq73-w596-rgm5, MINI-v2j4-95cc-vq33.