Description
LightLLM through 1.2.0 contains a memory exhaustion vulnerability in the NCCL control channel when started with --pd_trans_mode nccl, allowing unauthenticated attackers to exhaust KV-transfer worker memory. Attackers can call the exposed_set_value method to store unbounded key-value pairs without size limits, causing the worker process to crash and triggering node failure.
Affected products
Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.
ModelTC LightLLM
Default version status: unaffected
0 to ≤ 1.2.0affected
pkg:github/ModelTC/lightllmReferences
- https://github.com/ModelTC/LightLLM/issues/1595 ↗
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/router/model_infer/mode_backend/pd/nccl_kv_transporter.py#L416-L420 ↗
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/router/model_infer/mode_backend/pd/nccl_kv_transporter.py#L474-L485 ↗
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/router/model_infer/mode_backend/pd/base_kv_move_manager.py#L121-L122 ↗
- https://github.com/ModelTC/LightLLM ↗
- https://www.vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-memory-exhaustion-via-nccl-control-channel-set-value ↗