Vulnerability · CVE-2026-21869
llama.cpp is an inference of several LLM models in C/C++.
Published Jan 7, 2026 · catalog updated Jan 8, 2026 · llama.cpp is an inference
Last checked Nov 6, 2026. A connected source was read within the last 7 days.
Check if you run it
No confirmed exploitation is on record for CVE-2026-21869. EPSS is 0.53%. Act only if a listed version of llama.cpp is an inference is installed.
Gaps on this record
- The stored product name is a package slug. The name on this page is taken from the title (llama.cpp is an inference).
- No version range is stored. A customer cannot check an installed version against this record.
- No vendor fix or required action is stored. Compare the linked advisory before you change production.
Same product and reporting
- CVE-2026-43630 · Medium
- CVE-2026-34159 · Critical
- CVE-2026-33298 · High
- CVE-2026-27940 · High
- CVE-2026-2069 · Medium
- Severity
- High8.8
- Known exploitation
- Not in CISA/VulnCheck KEV
- EPSS
- 0.53%
- Remediation
- Advisory link
- Affected products
- vendor ggml-org llama.cpp ≤ 55d4206c8
llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fills up, llama_memory_seq_rm/add receives a reversed range and negative offset, causing out-of-bounds memory writes in the token evaluation loop. This deterministic memory corruption can crash the process or enable remote code execution (RCE). There is no fix at the time of publication.
Are you affected?
Enter the version you run. The result uses only the ranges stored on this record.
The check returns affected, not affected, or incomplete. It does not guess a version that is missing from the record.
- vendor ggml-org llama.cpp ≤ 55d4206c8≤ 55d4206c8
How to fix CVE-2026-21869
No stored fix
No vendor fix text is stored. Use the linked advisory before you change production.
Version check
No version range is stored, so an installed version cannot be checked on this page.
Advisory
Open the cve_org record and follow its fix.
Official advisories
What to do
Three questions, each answered from this record only. Confirm the vendor advisory before you patch.
Should you patch?
No confirmed exploitation is on record for CVE-2026-21869. EPSS is 0.53%. Act only if a listed version of llama.cpp is an inference is installed.
Which versions are affected?
Compare what you have installed with ggml-org llama.cpp ≤ 55d4206c8 ≤ 55d4206c8. Compare the installed version with the linked vendor advisory before you change production.
What should an analyst verify?
No weakness class is stored. EPSS 0.53%. There is no CISA KEV listing. No Exploit-DB or Metasploit reference is linked. Use the source links for the original advisory.
Code
The project this record applies to. Exploit listings stay in References.
Timeline
Detection, updates, and resolution for this record.
Jan 7, 2026 · EUVD
Detected
llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fills up, llama_memory_seq_rm/add receives a reversed range and negative offset, causing out-of-bounds mem
Jan 8, 2026 · EUVD
Updated
llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fills up, llama_memory_seq_rm/add receives a reversed range and negative offset, causing out-of-bounds mem
Sources
- CVE.orgVulnerability recordCVE-2026-21869
Official CVE identifier
cve.org - FIRST EPSSExploitation probabilityCVE-2026-21869
30-day exploitation probability 0.53%
first.org - EUVDVulnerability recordEUVD-2026-1661
llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied an
euvd.enisa.europa.eu
References
Freshness
Last verified in this catalog Nov 6, 2026. Significant claims (KEV, EPSS, CVSS, affected ranges) come from the source rows above — open the original publisher for the authoritative advisory.
- FIRST EPSSNov 6, 2026
- CVE.orgOct 31, 2026
- EUVDOct 30, 2026