CyberRota Analysis
AI-GeneratedInternLM LMDeploy versions up to 0.17.0 are vulnerable to an assertion error in the DistServe decode migration loop, allowing unauthenticated attackers to crash the inference engine by submitting a migration request with an empty remote_block_ids list. This vulnerability can disrupt service availability, leading to denial of service for inference requests. Organizations utilizing this software should prioritize patching to mitigate the risk of exploitation.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
InternLM LMDeploy through 0.17.0 contains a reachable assertion vulnerability in the DistServe decode migration loop that allows unauthenticated attackers to terminate the inference engine. Attackers can submit a migration_request with an empty remote_block_ids list to trigger an AssertionError that crashes the engine loop and causes subsequent inference requests to fail.