Data exposure via ZeroMQ on multi-node vLLM deployment

ImpactIn a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purposes. The primary vLLM host opens an XPUB ZeroMQ socket and binds it to ALL interfaces. While the socket is always opened for a multi-node deployment, it is only used when doing tensor parallelism across...

PYSEC-2026-2025 vLLM Denial of Service via the best_of parameter

A vulnerability was found in the ilab model serve component, where improper handling of the bestof parameter in the vllm JSON web API can lead to a Denial of Service DoS. The API used for LLM-based sentence or chat completion accepts a bestof parameter to return the best completion from several...

Uncaught Exception

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Uncaught Exception through the rejection sampler process. An attacker can cause the engine worker to crash and abort concurrent requests by sending...

Allocation of Resources Without Limits or Throttling

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling in the request.file.read process. An attacker can exhaust system memory or cause process...

Reachable Assertion

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Reachable Assertion via the /v1/completions endpoint when processing pure prompt embeds with M-RoPE models. An attacker can cause the server to cras...

PYSEC-2026-2303

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...

PYSEC-2026-2303

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...

CVE-2026-55514

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...

CVE-2026-54234

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then convert...

CVE-2026-55646

vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLMMAXAUDIOCLIPFILESIZEMB...

CVE-2026-55514

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...

CVE-2026-55514

CVE-2026-55514 affects the vLLM library (inference/serving) from versions 0.12.0 through older than 0.24.0. Sending a pure prompt embeds payload in a /v1/completions request for a model using M-RoPE triggers an EngineCore assertion, causing a fatal crash that shuts down the entire server applicat...

CVE-2026-55574 vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structuredoutputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the stri...

CVE-2026-54234

CVE-2026-54234 affects vLLM prior to version 0.24.0. A frontend multi-request speculative decoding path could cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which becomes negative one when the next live token is selected. This out-of-vo...

CVE-2026-54234 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then convert...

CVE-2026-55646 vLLM speech-to-text endpoints allocate full upload before enforcing the audio file-size limit

vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLMMAXAUDIOCLIPFILESIZEMB...

CVE-2026-55646 vLLM speech-to-text endpoints allocate full upload before enforcing the audio file-size limit

vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLMMAXAUDIOCLIPFILESIZEMB...

CVE-2026-55646

CVE-2026-55646 (vLLM) affects vLLM versions 0.22.0–0.23.0. The routes /v1/audio/transcriptions and /v1/audio/translations call request.file.read() to fully materialize an uploaded audio file before enforcing the documented size limit (default 25 MB). This can cause the server to allocate memory p...

PT-2026-55999

Name of the Vulnerable Software and Affected Versions vLLM versions 0.12.0 through 0.23.x Description A flaw in the EngineCore of the library occurs when a remote authorized user sends a pure prompt embeds payload to the '/v1/completions' endpoint using a model that implements M-RoPE Multimodal...

PT-2026-56000

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.24.0 Description The structured outputs.regex API parameter allows user-supplied regular expression strings to be passed to grammar compiler backends without a compilation timeout or complexity analysis. In the xgramma...