vLLMPYSEC-2026-4008
vLLM: attacker could allocate unbounded memory
UnratedCVE-2026-94626 · Published Sep 21, 2026 · updated Sep 30, 2026
vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tp_size values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel OOM-kill of the decode worker process.
Affected versions
| Package | Affected | Fixed in |
|---|---|---|
| vllm PyPI | < 0.30.0 | 0.30.0 |
Details and references
- CVSS 4.0
- CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
- Severity from
- no source yet
- Also known as
- CVE-2026-94626
- github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/utils.py#L569-L573
- github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/metadata.py#L277
- www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-unvalidated-nixl-tp-size
- github.com/vllm-project/vllm/pull/51137
- github.com/vllm-project/vllm
More vLLM advisories
All vLLM| Date | Advisory | Severity | Fixed in |
|---|---|---|---|
| Sep 21 | vLLM: denial of service High7.5Sep 21 | High7.5 | 0.30.0 |
| Sep 21 | vLLM: denial of serviceHigh7.5Sep 21 | High7.5 | 0.30.0 |
| Sep 21 | vLLM: resource exhaustionMedium5.3Sep 21 | Medium5.3 | 0.30.0 |
| Sep 21 | vLLM: denial of serviceUnratedSep 21 | Unrated | 0.30.0 |
| Sep 19 | vLLM through 0.29.0 fails to properly validate bad_words token indices against...Medium4.3Sep 19 | Medium4.3 | 0.30.0 |
| Sep 18 | vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead...Medium5.3Sep 18 | Medium5.3 | 0.29.0 |