CVE-2026-92971InternLM lmdeploy
NVD
Vulnerability Summary
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 v4.0 Base Metrics — Score 8.7 (HIGH)
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:NAttack VectorNetwork
Attack ComplexityLow
Attack RequirementsNone
Privileges RequiredNone
User InteractionNone
Confidentiality (Vulnerable System)None
Integrity (Vulnerable System)None
Availability (Vulnerable System)High
Confidentiality (Subsequent System)None
Integrity (Subsequent System)None
Availability (Subsequent System)None
Show CVSS v3.x metrics (score 7.5)
CVSS v3.1 Base Metrics — Score 7.5 (HIGH)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:HAttack VectorNetwork
Attack ComplexityLow
Privileges RequiredNone
User InteractionNone
ScopeUnchanged
ConfidentialityNone
IntegrityNone
AvailabilityHigh
Affected & Patched Versions
- InternLM lmdeploy <= 0.17.0
- InternLM lmdeploy 0.17.0
What to do
Plan remediation soon. No exploitation is confirmed yet, but the severity is high.
- Check whether you run InternLM lmdeploy and which version.
- Update to a patched version listed above, then confirm the new version.
Timeline
- Sep 17, 2026Published
- Sep 17, 2026Record last modified
Score, severity and exploitation changes are tracked from the day Watchtower started logging them.
Get notified about new InternLM lmdeploy CVEsYou are reading CVE-2026-92971. Get an email when KEV listings, exploits or new CVEs match your stack.
Set up CVE alertsMore InternLM lmdeploy CVEs
External References
- Issue Trackinghttps://github.com/InternLM/lmdeploy/issues/4965
- Referencehttps://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/pytorch/engine/engine_loop.py#L560-L564
- Referencehttps://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/serve/openai/endpoints/completions.py#L130-L136
- Referencehttps://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/pytorch/utils.py#L187-L214
- Referencehttps://github.com/InternLM/lmdeploy
- Referencehttps://www.vulncheck.com/advisories/internlm-lmdeploy-through-0.17.0-assertion-denial-of-service
Data last checked: Nov 17, 2026 19:13 UTC