Description (CNA)
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 (CNA)
| Vendor / product | Versions |
|---|---|
| ModelTC / LightLLM | affected 0 through 1.2.0 |
CWE
CWE-770
References
- 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
ADP enrichment
No English description supplied.