CVE-2026-92971
InternLM LMDeploy through 0.17.0 Assertion Denial of Service
CVSS 4.0 8.7 HIGHCVSS 3.1 7.5 HIGHCheck source for fixed versionsKEV status unknown
cve-program · CVE-2026-92971
PublishedInternLM 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.
Read the publisher's advisoryAffected versions, risk and source history
Related advisories and sources
Publishers link these advisories through the identifiers shown below. A shared identifier or date alone does not tell you whether your software is affected or whether the advisories describe the same cause.
CVE-2026-92971 · CVE overview and exploitation status
cve-program · CVE-2026-92971
- https://github.com/InternLM/lmdeploy/issues/4965
- https://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/pytorch/engine/engine_loop.py#L560-L564
- https://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/serve/openai/endpoints/completions.py#L130-L136
- https://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/pytorch/utils.py#L187-L214
- https://github.com/InternLM/lmdeploy
- https://www.vulncheck.com/advisories/internlm-lmdeploy-through-0.17.0-assertion-denial-of-service
Related changes
Linked by CVE identifierNo related changes are available here.