CVE-2026-116176

vLLM 0.9.2 before 0.24.0 SSRF via X-Request-Id in P2pNcclConnector

vLLM from 0.9.2 before 0.24.0 contains a server-side request forgery vulnerability that allows API callers to force outbound connections by embedding a decode address in the X-Request-Id header. Attackers can make a P2pNcclConnector prefill worker ZMQ-connect to an attacker host, leaking the NCCL unique_id and KV-cache tensors or blocking the worker.

CVSS 4.0 · 8.8 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-116172

vLLM 0.22.0 before 0.24.0 DoS via Rust gRPC CandidateTokens.top_n

vLLM from 0.22.0 before 0.24.0 contains an improper input validation vulnerability in the Rust gRPC converter that allows remote attackers to bypass max_logprobs limits via CandidateTokens.top_n. Attackers can send Generate or GenerateStream requests with oversized or integer-wrapping top_n values to trigger torch.topk failures that terminate EngineCore.

CVSS 4.0 · 8.2 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-115916

vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-115913

vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the Phi-4 multimodal audio encoder in phi4mm_audio.py and phi4mm_utils.py uses eager attention by default, allowing a remote client to submit one legal long audio clip that causes MultiHeadedAttention.forward_attention to materialize and retain full attention matrices in self.attn. The scaled dot-product attention branch does not materialize these matrices. The resulting quadratic GPU-memory use can cause an out-of-memory condition and terminate EngineCore for all users. This issue is fixed in version 0.32.0.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-115917

vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim's browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. This issue is fixed in version 0.32.0.

CVSS 3.1 · 3.4 Low EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-115918

vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-115914

vLLM DeepSeek-OCR image processing vulnerable to denial of service

vLLM is an inference and serving engine for large language models. From 0.11.1 until 0.32.0, the DeepSeek-OCR, DeepSeek-OCR-2, and Unlimited-OCR image path allows a remote client that can reach the OpenAI-compatible API to submit a legal image whose normalized pixels sum to zero when that image is alone in its per-step encoder batch. _parse_and_validate_image_input returns no embedding, embed_multimodal propagates that value, and sanity_check_mm_encoder_outputs triggers a fatal assertion that shuts down the engine for all users. This issue is fixed in version 0.32.0.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-115911

vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-116181

vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids

vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-116177

vLLM 0.10.2 before 0.25.0 DoS via Nemotron-VL Processor Decompression-Bomb Guard Bypass

vLLM from 0.10.2 before 0.25.0 contains an uncontrolled resource consumption vulnerability that allows unauthenticated attackers to exhaust memory because the Nemotron-VL processors globally set Image.MAX_IMAGE_PIXELS to None. Attackers can submit a pathological decompression-bomb image to /v1/chat/completions to OOM-kill the worker and deny service to co-tenants.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-116174

vLLM 0.22.0 before 0.24.0 Denial of Service via Rust gRPC Generate

vLLM from 0.22.0 before 0.24.0 contains an improper input validation vulnerability in the Rust gRPC Generate and GenerateStream service that forwards unchecked prompt token IDs to EngineCore. Attackers can submit requests with out-of-vocabulary prompt.token_ids values to trigger a fatal embedding lookup failure that terminates EngineCore and leaves the server unhealthy.

CVSS 4.0 · 8.2 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-114054

vLLM before 0.31.0 Cross-Request Cache Aliasing via EXIF ImageID and Prefix-Cache Keys

vLLM before 0.31.0 contains a cache aliasing vulnerability that allows authenticated attackers to collide shared cache keys by supplying caller-controlled values such as EXIF ImageID or cache_salt. Attackers can set a UUID EXIF ImageID to receive another request's cached processed media, or match cache_salt to a LoRA name to reuse first-block KV state.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-114051

vLLM before 0.31.0 Denial of Service via min_tokens in /inference/v1/generate

vLLM before 0.31.0 skips the min_tokens <= max_tokens check for /inference/v1/generate requests with a null max_tokens, so the EngineCore input thread later dies on an uncaught VLLMValidationError while /health still returns 200. Unauthenticated remote attackers can send one request with an oversized min_tokens to hang all subsequent generation requests until manual restart.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-114049

vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense

vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stale allowed_token_ids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycled batch slots apply their token allowlist to victims' unrestricted requests.

CVSS 4.0 · 6.3 Medium EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-115912

vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-out deployments with shared-memory multimodal caching enabled, workers trust those values and pass attacker-selected bytes to pickle.loads(), allowing arbitrary Python execution even when insecure serialization is disabled. This issue is fixed in version 0.32.0.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-115915

vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to Pillow through Image.open(BytesIO(data)) without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request paths through parse_image() and fetch_image() can therefore dispatch an EPS payload to host components. A host with Ghostscript affected by CVE-2024-29510 can execute commands with the vLLM process's privileges, while environments using Pillow 12.0.0 through 12.2.0 can trigger CVE-2026-59203 and exhaust media-loading workers. Deployments without the applicable vulnerable dependency are not affected by that corresponding impact. This issue is fixed in version 0.32.0.

CVSS 3.1 · 8.1 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-114053

vLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision

vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mm_processor_kwargs.code_revision to Transformers AutoProcessor.from_pretrained, letting clients select which revision of a model's dynamic processor code is imported when trust_remote_code is enabled. An attacker controlling a revision in the served model repository can send a multimodal request to the unauthenticated /tokenize endpoint to execute arbitrary Python in the vLLM API process.

CVSS 4.0 · 9.2 Critical EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-116180

vLLM from 0.8.5 before 0.31.0 Cross-Tenant DoS via Uninitialized LogprobsTensors

vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py allocates an uninitialized int32 tensor, and the V1 model runner leaves prompt positions reported as computed by a KV connector unwritten. A client sharing the engine can send prompt_logprobs (or echo with logprobs) against a connector-cached prefix, making tokenizer decode raise OverflowError, which crashes EngineCore and drops all co-tenant requests.

CVSS 4.0 · 8.3 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-116178

vLLM 0.20.0 before 0.30.0 DoS via /inference/v1/generate mm_placeholders

vLLM from 0.20.0 before 0.30.0 contains a denial of service vulnerability that allows remote attackers to crash the engine by sending inconsistent multimodal metadata to the disaggregated /inference/v1/generate endpoint. Attackers can replay a valid multimodal item with repeated or overlapping mm_placeholders ranges or mismatched kwargs_data and mm_hashes lists, producing a negative text span in Qwen2.5-VL position construction that terminates the engine.

CVSS 4.0 · 8.2 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-116173

vLLM 0.22.0 before 0.24.0 Denial of Service via gRPC output_candidates.token_ids

vLLM from 0.22.0 before 0.24.0 contains a denial of service vulnerability that allows remote attackers to terminate EngineCore by bypassing logprob_token_ids limits in the Rust gRPC frontend. Attackers can send Generate or GenerateStream requests with output_logprobs enabled and more than 128 output_candidates.token_ids, triggering a fatal sampler exception that crashes the engine.

CVSS 4.0 · 8.2 High EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm