Inference interruption via unvalidated logit bias
Published Jul 14, 2026 · Updated Jul 14, 2026
Reachable assertion in NVIDIA TensorRT-LLM 1.3.0rc15 and earlier allows local users to interrupt inference via crafted logit bias. The OpenAI-compatible chat, completion, and chat_harmony paths passed logit_bias token IDs and values into sampling without complete bounds and finiteness validation. Local access to the inference API is required, and the resulting sampler-thread assertion interrupts availability without reported data exposure or modification.
Summary
What happened
Reachable assertion in NVIDIA TensorRT-LLM 1.3.0rc15 and earlier allows local users to interrupt inference via crafted logit bias. The OpenAI-compatible chat, completion, and chat_harmony paths passed logit_bias token IDs and values into sampling without complete bounds and finiteness validation. Local access to the inference API is required, and the resulting sampler-thread assertion interrupts availability without reported data exposure or modification.
The record
- CVE
- CVE-2026-47475
- Published
- Jul 14, 2026
- Updated
- Jul 14, 2026
- Vendor
- DPDK Project
- Product
- TensorRT-LLM
- Classifications
- CWE-617, T1499.004
- Attack vector
- local
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 14, 2026CVE publishedPublication date reported by the CVE source.
- Jul 14, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0.0 <=v1.3.0 rc15
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo