● PyPI package
vllm, page 2
Vllm has 113 security advisories. The newest release any of them names as the fix is 0.32.0.
As of , vllm has 113 security advisories. The newest release any of them names as the fix is 0.32.0.
| Advisory | What it is | Affects | Fixed in | Published |
|---|---|---|---|---|
| CVE-2025-32444GHSA-hj4w-hm2g-p6w5, PYSEC-2025-42 | vLLM Vulnerable to Remote Code Execution via Mooncake IntegrationCritical severity | From 0.6.5 before 0.8.5 | 0.8.5 | |
| CVE-2025-30202GHSA-9f8f-2vmf-885j, PYSEC-2026-2016 | Data exposure via ZeroMQ on multi-node vLLM deploymentHigh severity | From 0.5.2 before 0.8.5 | 0.8.5 | |
| GHSA-ggpf-24jw-3fcw | CVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0Critical severity | Before 0.8.0 | 0.8.0 | |
| GHSA-hf3c-wxg2-49q9 | vLLM vulnerable to Denial of Service by abusing xgrammar cacheModerate severity | From 0.6.5 before 0.8.4 | 0.8.4 | |
| CVE-2024-9052GHSA-pgr7-mhp5-fgjp, PYSEC-2026-568 | vLLM deserialization vulnerability in vllm.distributed.GroupCoordinator.recv_objectCritical severity | Up to and including 0.8.1 | No fixed version listed | |
| CVE-2024-11041GHSA-5vqr-wprc-cpp7, PYSEC-2026-566 | vLLM Deserialization of Untrusted Data vulnerabilityCritical severity | Up to and including 0.6.2 | No fixed version listed | |
| CVE-2024-9053GHSA-cj47-qj6g-x7r4, PYSEC-2025-222 | vLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypointsCritical severity | Up to and including 0.6.0 | No fixed version listed | |
| CVE-2025-29783GHSA-x3m8-f7g5-qhm7, PYSEC-2025-63 | vLLM Allows Remote Code Execution via Mooncake IntegrationCritical severity | From 0.6.5 before 0.8.0 | 0.8.0 | |
| CVE-2025-29770GHSA-mgrm-fgjv-mhv8, PYSEC-2025-223 | vLLM denial of service via outlines unbounded cache on diskModerate severity | Before 0.8.0 | 0.8.0 | |
| CVE-2025-25183GHSA-rm76-4mrf-v9r8, PYSEC-2025-62 | vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cacheLow severity | Before 0.7.2 | 0.7.2 | |
| CVE-2025-24357GHSA-rh4j-5rhw-hr54, PYSEC-2025-58 | vllm: Malicious model to RCE by torch.load in hf_model_weights_iteratorHigh severity | Before 0.7.0 | 0.7.0 | |
| CVE-2024-8768GHSA-w2r7-9579-27hf, PYSEC-2026-2024 | vLLM denial of service vulnerabilityHigh severity | Before 0.5.5 | 0.5.5 | |
| CVE-2024-8939GHSA-wc36-9694-f9rf, PYSEC-2026-2025 | vLLM Denial of Service via the best_of parameterModerate severity | Up to and including 0.5.0.post1 | No fixed version listed |