Bug 2569886 (CVE-2026-124994)

Summary: CVE-2026-124994 exllamav3: exllamav3: Information disclosure via out-of-bounds read in ngram_dequant
Product: [Other] Security Response Reporter: OSIDB Bzimport <bzimport>
Component: vulnerabilityAssignee: Product Security DevOps Team <prodsec-dev>
Status: NEW --- QA Contact:
Severity: medium Docs Contact:
Priority: medium    
Version: unspecifiedKeywords: Security
Target Milestone: ---   
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: ---
Doc Text:
A flaw was found in exllamav3. A remote attacker can exploit this vulnerability by supplying a manipulated head_bias parameter to the ngram_dequant function in the NGramEmbedding component. This causes an out-of-bounds read, where the application reads data outside its allocated memory boundaries. Successful exploitation may allow an attacker to disclose sensitive memory contents or crash the application, leading to a Denial of Service (DoS).
Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:

Description OSIDB Bzimport 2026-11-10 19:21:57 UTC
A security flaw has been discovered in Turboderp-org ExLlamaV3 up to 1.6.3. The affected element is the function ngram_dequant of the file exllamav3/exllamav3_ext/ngram.cu of the component NGramEmbedding. The manipulation of the argument head_bias results in out-of-bounds read. The attack may be launched remotely. The exploit has been released to the public and may be used for attacks. Upgrading to version 1.6.4 is sufficient to fix this issue. The patch is identified as c9a57ae832a3035e264e0a412e1daf4ebb699b98. It is suggested to upgrade the affected component.