Vulnerability 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.
CVSS Score
HIGH
Related Weaknesses (CWE)
References
- https://github.com/InternLM/lmdeploy
- https://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/pytorch/engine/engine
- https://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/pytorch/utils.py#L187
- https://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/serve/openai/endpoint
- https://github.com/InternLM/lmdeploy/issues/4965
- https://www.vulncheck.com/advisories/internlm-lmdeploy-through-0.17.0-assertion-
- https://github.com/InternLM/lmdeploy/issues/4965
FAQ
What is CVE-2026-92971?
CVE-2026-92971 is a vulnerability with a CVSS score of 7.5 (HIGH). 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 ...
How severe is CVE-2026-92971?
CVE-2026-92971 has been rated HIGH with a CVSS base score of 7.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-92971?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.