High severity · published Sep 17, 2026
CVE-2026-92971
InternLM LMDeploy through 0.17.0 Assertion Denial of Service
7.5
CVSS
0.7%
EPSS
No
On KEV
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 vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
None
Integrity
None
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.7% · higher than 53% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LM
lmdeploy · InternLM
through 0.17.0 · source: vendor
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-92971
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-92971
github.com
https://github.com/InternLM/lmdeploy
github.com
https://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/pytorch/engine/engine_loop.py#L560-L564
github.com
https://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/pytorch/utils.py#L187-L214
github.com
https://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/serve/openai/endpoints/completions.py#L130-L136
github.com
https://github.com/InternLM/lmdeploy/issues/4965
www.vulncheck.com
https://www.vulncheck.com/advisories/internlm-lmdeploy-through-0.17.0-assertion-denial-of-service
More from lmdeploy
9.8
CVE-2025-66455
LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py
9.8
CVE-2025-59953
LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy
9.8
CVE-2026-76850
LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector
8.8
CVE-2026-33625
LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
8.8
CVE-2025-67729
lmdeploy vulnerable to Arbitrary Code Execution via Insecure Deserialization in torch.load()