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 VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed upload size limit (default 25 MB) later in the speech-to-text preprocessing step, so an API caller who can reach those routes can submit an oversized multipart upload and cause vLLM to allocate memory proportional to the uploaded file size before the request is rejected as too large, creating memory pressure or terminating the process depending on deployment resource limits. This issue is fixed in version 0.24.0.

CVSS 3.1 · 6.5 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

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 converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0.

CVSS 3.1 · 7.5 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

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 structured_outputs.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 string reaches the regex compiler with no guard, and in the outlines backend the validation step blocks structural issues such as lookarounds and backreferences but performs no complexity analysis, so a pattern with nested quantifiers passes all checks and causes exponential state-space expansion, allowing a single request containing an adversarial regex to hang an inference worker indefinitely and deny service. This issue is fixed in version 0.24.0.

CVSS 4.0 · 8.7 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-55514

vLLM denial of service via prompt embeds on M-RoPE models

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 authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.

CVSS 4.0 · 7.1 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-53923

vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow

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/gguf_kernel.cu) causes partial tensor processing. The output tensor is allocated at full size via torch::empty (uninitialized memory), but the dequantize CUDA kernel processes only a truncated number of elements. The unfilled portion of the output tensor retains whatever was previously in GPU memory. In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure. This vulnerability is fixed in 0.23.1rc0.

CVSS 4.0 · 5.3 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-54232

vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is vulnerable to a dependency confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the package name was not registered on PyPI, and UV_INDEX_STRATEGY="unsafe-best-match" is set globally. An attacker who registers flashinfer-jit-cache on PyPI with version 0.6.11.post2 can execute arbitrary code as root during the Docker build and backdoor every resulting container image, enabling exfiltration of all user prompts, API credentials, and model data from production vLLM deployments This vulnerability is fixed in 0.22.1.

CVSS 3.1 · 8.8 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-47155

vLLM: Artifact Pin Decay in vLLM allows pinned deployments to load unpinned code, weights, and processors

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 processors, retrieval side weights, or same-repository subfolder weights/config from an unpinned/default revision. This is a supply-chain integrity issue for pinned vLLM deployments. Operators can believe they are serving a reviewed model revision while vLLM resolves behavior-affecting nested or sibling artifacts outside that reviewed revision. This vulnerability is fixed in 0.22.0.

CVSS 3.1 · 6.5 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-54236

vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router

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 sanitize_message helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo str(exc) directly to clients without calling sanitize_message. The unsanitized sites include the Anthropic API router in vllm/entrypoints/anthropic/api_router.py (the POST /v1/messages and POST /v1/messages/count_tokens handlers), the Server-Sent Events streaming converter in vllm/entrypoints/anthropic/serving.py, and the realtime speech-to-text WebSocket in vllm/entrypoints/speech_to_text/realtime/connection.py. These paths catch the exception inside the route coroutine and construct the JSONResponse themselves, bypassing the sanitizing global FastAPI exception handler, and WebSocket frames do not traverse that handler chain at all. Using the same primitive as the parent issue, an unauthenticated attacker can send malformed image bytes through the Anthropic Messages API image content parts so that PIL.Image.open raises an UnidentifiedImageError whose message contains the BytesIO object repr, leaking the heap memory address verbatim in the error.message field of the response body. This vulnerability is fixed in 0.23.1rc0.

CVSS 3.1 · 5.3 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-54235

vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

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 propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors that can crash the inference worker. This vulnerability is fixed in 0.23.1rc0.

CVSS 4.0 · 6.9 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-54233

vLLM: OOM Denial of Service via Audio Decompression Bomb

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.

CVSS 3.1 · 6.5 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-44223

vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters

vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.

CVSS 3.1 · 6.5 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-5497

Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm

vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication.

CVSS 3.1 · 7.5 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-4944

Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control

vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`vllm/model_executor/models/nemotron_vl.py` and `vllm/model_executor/models/kimi_k25.py`). This bypasses the user's explicit `--trust-remote-code=False` setting, enabling remote code execution via malicious HuggingFace model repositories. This issue is an incomplete fix for CVE-2025-66448 and CVE-2026-22807, as it affects separate code paths in model implementation files. Deployments loading NemotronVL or KimiK25 models are particularly impacted.

CVSS 3.0 · 8.8 High EPSS < 1% KEV · Not listed

Vendors

Vllm-project

Products

Vllm

CVE-2026-9540

vllm-project vllm OpenAI-compatible Serving Path denial of service

A vulnerability was identified in vllm-project vllm 0.19.0. This issue affects some unknown processing of the component OpenAI-compatible Serving Path. Such manipulation leads to denial of service. It is possible to launch the attack remotely. The exploit is publicly available and might be used. The pull request to fix this issue awaits acceptance.

CVSS 4.0 · 6.9 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm-project

Products

Vllm

CVE-2026-44222

vLLM: Remote DoS via Special-Token Placeholders

vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0.

CVSS 3.1 · 6.5 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-34760

vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing (to_mono), while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results in inconsistency between audio heard by humans (e.g., through headphones/regular speakers) and audio processed by AI models (Which infra via Librosa, such as vllm, transformer). This issue has been patched in version 0.18.0.

CVSS 3.1 · 5.9 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-34753

vLLM affected by Server-Side Request Forgery (SSRF) in `download_bytes_from_url `

vLLM is an inference and serving engine for large language models (LLMs). From 0.16.0 to before 0.19.0, a server-side request forgery (SSRF) vulnerability in download_bytes_from_url allows any actor who can control batch input JSON to make the vLLM batch runner issue arbitrary HTTP/HTTPS requests from the server, without any URL validation or domain restrictions. This can be used to target internal services (e.g. cloud metadata endpoints or internal HTTP APIs) reachable from the vLLM host. This vulnerability is fixed in 0.19.0.

CVSS 3.1 · 5.4 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-22773

vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions

vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime error, leading to complete server termination. This issue has been patched in version 0.12.0.

CVSS 3.1 · 6.5 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-22807

vLLM affected by RCE via auto_map dynamic module loading during model initialization

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.

CVSS 3.1 · 8.8 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-24779

vLLM vulnerable to Server-Side Request Forgery (SSRF) in `MediaConnector`

vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.14.1, a Server-Side Request Forgery (SSRF) vulnerability exists in the `MediaConnector` class within the vLLM project's multimodal feature set. The load_from_url and load_from_url_async methods obtain and process media from URLs provided by users, using different Python parsing libraries when restricting the target host. These two parsing libraries have different interpretations of backslashes, which allows the host name restriction to be bypassed. This allows an attacker to coerce the vLLM server into making arbitrary requests to internal network resources. This vulnerability is particularly critical in containerized environments like `llm-d`, where a compromised vLLM pod could be used to scan the internal network, interact with other pods, and potentially cause denial of service or access sensitive data. For example, an attacker could make the vLLM pod send malicious requests to an internal `llm-d` management endpoint, leading to system instability by falsely reporting metrics like the KV cache state. Version 0.14.1 contains a patch for the issue.

CVSS 3.1 · 7.1 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm