CVE-2026-54233: Improper Handling of Highly Compressed Data (Data Amplification)

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.23.1rc0, vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to 14.9GB of float32 PCM at decode time. This vulnerability is fixed in 0.23.1rc0...

CVE-2026-54236: Insertion of Sensitive Information into Log File

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitizemessage helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo...

CVE-2026-53923: Incorrect Conversion between Numeric Types

vLLM is an inference and serving engine for large language models LLMs. From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels csrc/quantization/gguf/ggufkernel.cu causes partial tensor processing. The output tensor is allocated at full size via...

CVE-2026-41523: Improper Control of Generation of Code

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLL...

CVE-2026-47155: Insufficient Verification of Data Authenticity

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.22.0, vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies --revision or --code-revision can still load dynamic code, GGUF files, image...

CVE-2026-54235: Improper Validation of Specified Type of Input

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.23.1rc0, ll temperature validation gates use comparison operators , which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagat...

GHSA-VFM7-4H43-GP6M Duplicate Advisory: vLLM Vulnerable to Regular Expression Denial of Service

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-j828-28rj-hfhp. This link is maintained to preserve external references. Original Description vLLM versions = 0.6.3 and 0.9.0 contain multiple regular expression denial of service ReDoS vulnerabilities. Several...

Duplicate Advisory: vLLM introduced enhanced protection for CVE-2025-62164

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-mcmc-2m55-j8jj. This link is maintained to preserve external references. Original Description vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because...

Duplicate Advisory: vLLM Vulnerable to Regular Expression Denial of Service

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-j828-28rj-hfhp. This link is maintained to preserve external references. Original Description vLLM versions = 0.6.3 and 0.9.0 contain multiple regular expression denial of service ReDoS vulnerabilities. Several...

GHSA-78FP-CF4H-G36P Duplicate Advisory: vLLM introduced enhanced protection for CVE-2025-62164

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-mcmc-2m55-j8jj. This link is maintained to preserve external references. Original Description vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because...

CVE-2025-71379

vLLM versions = 0.6.3 and 0.9.0 contain multiple regular expression denial of service ReDoS vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker...

CVE-2026-56340 vLLM - Denial of Service via Unvalidated Multimodal Embeddings

vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed negative or out-of-bounds tensor indices, when the...

CVE-2026-56340

vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed negative or out-of-bounds tensor indices, when the...

EUVD-2026-38129

vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed negative or out-of-bounds tensor indices, when the...

CVE-2026-56340 vLLM - Denial of Service via Unvalidated Multimodal Embeddings

vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed negative or out-of-bounds tensor indices, when the...

CVE-2026-56340

vLLM versions >= 0.10.2 and

CVE-2025-71379

CVE-2025-71379 affects vLLM versions 0.6.3 through 0.8.x (before 0.9.0). The vulnerability is a set of regular expression denial of service (ReDoS) flaws in multiple components: (1) regex patterns in vllm/lora/utils.py, (2) the phi4mini tool parser, and (3) the OpenAI-compatible serving chat endp...

CVE-2025-71379

vLLM versions = 0.6.3 and 0.9.0 contain multiple regular expression denial of service ReDoS vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker...

EUVD-2025-210290

vLLM versions = 0.6.3 and 0.9.0 contain multiple regular expression denial of service ReDoS vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker...

CVE-2025-71379 vllm - Regular Expression Denial of Service in Multiple Components

vLLM versions = 0.6.3 and 0.9.0 contain multiple regular expression denial of service ReDoS vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker...