High severity · published Sep 17, 2026
CVE-2026-92983
InternLM LMDeploy through 0.17.0 Memory Exhaustion via Session ID Mismatch
7.5
CVSS
0.7%
EPSS
No
On KEV
Description
InternLM LMDeploy through 0.17.0 in DistServe prefill/decode disaggregation mode fails to release scheduler sessions because the proxy uses user-facing session IDs instead of internal scheduler keys. Unauthenticated attackers can send completion requests to the proxy endpoint that accumulate unreleased scheduler metadata and memory until the prefill worker is out-of-memory killed.
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 51% 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
Affected product
LM
lmdeploy
InternLM
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()