CVE-2026-111160

CVSS 8.7 (high) · published 2026-10-15

LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pd_kv_trans_params field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in InferSamplingParams, killing the inference thread while /health stays up and all later requests hang until restart.

Weakness: CWE-502

Source: NVD CVE-2026-111160

References

• https://github.com/ModelTC/LightLLM
• https://github.com/ModelTC/LightLLM/issues/1629
• https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_lightllm.py#L37-L43
• https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/core/objs/sampling_params.py#L356-L357
• https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/router/model_infer/infer_batch.py#L484-L485
• https://www.vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-dos-via-pd-kv-trans-params-deserialization

Check your software

Connect an AI agent to the Fixlane MCP server or ask the Telegram bot to check what you have installed against incidents with a verified fixed version.