CVE-2026-100652

vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids

vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-100648

vllm before 0.29.0 Uncontrolled Resource Consumption via Audio Decoding

vllm before 0.29.0 fails to enforce VLLM_MAX_AUDIO_CLIP_FILESIZE_MB limit in multimodal chat audio decoding, allowing unauthenticated clients to bypass file size restrictions. Attackers can submit oversized audio files through chat endpoints to consume excessive memory and CPU resources during decoding.

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

Vendors

Vllm

Products

Vllm

CVE-2026-94625

vLLM through 0.29.0 Resource Exhaustion via Ownerless Mooncake Transfer Placeholders

vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests create ownerless transfer placeholders that are never reclaimed. Attackers can send rejected requests to exhaust sender task pools, causing valid requests to be delayed by up to 480 seconds while health checks continue returning success.

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

Vendors

Vllm

Products

Vllm

CVE-2026-93841

vLLM through 0.29.0 Adjacent-Request Sampler State Corruption via Unvalidated Prompt Token IDs

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.

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

Vendors

Vllm

Products

Vllm

CVE-2026-94627

vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision

vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Attackers can trigger GPU memory exhaustion by submitting completion requests with multiple prompts, causing orphaned KV cache blocks to accumulate until process restart and eventually preventing legitimate requests from executing.

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

Vendors

Vllm

Products

Vllm

CVE-2026-94624

vLLM through 0.29.0 Denial of Service via Unbounded P2P KV Offloading Sessions

vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can supply arbitrary remote host and port values in kv_transfer_params to create unreachable peer sessions that retain ZeroMQ sockets until the context quota is exhausted, causing an uncaught ZMQError that crashes EngineCore and stops all inference.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-94623

vLLM through 0.29.0 Denial of Service via NIXL Multi-Prompt Assertion Failure

vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation that fails to properly validate block counts across multi-prompt completion requests in prefill/decode disaggregated deployments. Attackers can trigger an assertion failure in NixlBaseConnectorWorker._apply_prefix_caching by submitting completion requests with multiple prompts of varying lengths, causing the decode worker to terminate and become unavailable until restarted.

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

Vendors

Vllm

Products

Vllm

CVE-2026-94622

vLLM through 0.29.0 Denial of Service via Incomplete NIXL KV Transfer Metadata

vLLM versions through 0.29.0 contain a denial of service vulnerability in the NIXL connector's metadata handling for prefill/decode disaggregated deployments. Attackers can send requests with incomplete kv_transfer_params dictionary entries to trigger an uncaught KeyError in EngineCore scheduling, causing the decode engine to terminate and making all routed requests fail until manual restart.

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

Vendors

Vllm

Products

Vllm

CVE-2026-93989

vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words

vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output width in SamplingParams.update_from_tokenizer(). Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to return incorrect tokens.

CVSS 4.0 · 2.3 Low EPSS < 1% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-93840

vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids

vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.

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

Vendors

Vllm

Products

Vllm

CVE-2026-93592

vLLM before 0.28.0 Denial of Service via negative token ID

vLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, allowing unauthenticated attackers to crash the engine by submitting negative token IDs. A single request with a negative token ID triggers a CUDA device-side assertion that poisons the GPU context, causing all subsequent requests to fail until the process restarts.

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

Vendors

Vllm

Products

Vllm

CVE-2026-93436

vLLM through 0.29.0 Memory Exhaustion via Rejected Requests

vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requests with max_tokens=0 to exhaust decode-worker memory without bound until the worker restarts.

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

Vendors

Vllm

Products

Vllm

CVE-2026-90554

vLLM before 0.28.0 Denial of Service via audio extraction

vLLM versions >=0.10.2 and <0.28.0 do not apply any audio decode-size or duration limit when extracting audio from video input for NanoNemotronVL models. In nano_nemotron_vl.py, _extract_audio_from_videos calls load_audio_pyav(BytesIO(video_bytes)) without the max_duration_s or max_decode_bytes parameters, so neither VLLM_MAX_AUDIO_DECODE_DURATION_S nor VLLM_MAX_AUDIO_DECODE_BYTES is enforced (unlike the direct audio upload path in AudioMediaIO). When a NanoNemotronVL model is served with use_audio_in_video=True, an attacker who supplies a small, highly compressed video as multimodal input can force the server to allocate gigabytes of memory during audio decoding, resulting in a denial of service. Fixed in vLLM 0.28.0.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-90553

vLLM before 0.28.0 Remote Code Execution via LlavaOnevision2 processor

vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers can craft a malicious model with arbitrary code in processing_llava_onevision2.py that executes with vLLM process authority even when trust_remote_code is set to False.

CVSS 4.0 · 8.5 High EPSS < 1% KEV · Not listed

Vendors

Vllm

Products

Vllm

CVE-2026-90555

vLLM before 0.28.0 Denial of Service via Audio Header

vLLM versions before 0.28.0 fail to validate audio sample rate headers in the transcription endpoint, allowing authenticated clients to bypass duration checks. Attackers can submit forged FLAC headers with inflated sample rates to trigger excessive memory allocation and crash the API server process affecting all tenants.

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

Vendors

Vllm

Products

Vllm

CVE-2026-41523

vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution

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 vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-48746

vLLM: OpenAI auth bypass

vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in ASGI web servers and starlette's trust on those web servers enables an authentication bypass of the OpenAI API AuthenticationMiddleware. It allows to use the API without providing the configured VLLM_API_KEY or --api-key. This vulnerability is fixed in 0.22.0.

CVSS 3.1 · 9.1 Critical EPSS 1.2% KEV · Not listed

Vendors

Vllm Vllm-project

Products

Vllm Vllm

CVE-2026-78684

vLLM before 0.27.0 Denial of Service via DeepStream Backend

vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in its decode path. Unauthenticated attackers can activate DeepStream at request time to initialize the process-wide GPU decode pool and submit video that bypasses resource controls, causing partial denial of service for concurrent requests.

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

Vendors

Vllm

Products

Vllm

CVE-2026-7141

vLLM KV Block kv_cache_interface.py has_mamba_layers uninitialized resource

A vulnerability was found in vLLM up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v1/kv_cache_interface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is considered to have high complexity. The exploitability is described as difficult. The exploit has been made public and could be used. The existence of this vulnerability is still disputed at present. The proposed patch did not fix the issue. A 3rd party explains: "The divergence could be explained by a benign and expected vLLM behavior where vLLM server could group concurrent requests together resulting in different input shapes based on varying request arrival time. The differences in grouped input shapes could call different kernels with could produce difference results due to rounding and differences in order of operations. There is an environment variable VLLM_BATCH_INVARIANT=1 for users that desire to have deterministic output with temperature 0.0."

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

Vendors

Vllm

Products

Vllm

CVE-2026-34756

vLLM Affected by Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an astronomically large n value. This completely blocks the Python asyncio event loop and causes immediate Out-Of-Memory crashes by allocating millions of request object copies in the heap before the request even reaches the scheduling queue. This vulnerability is fixed in 0.19.0.

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

Vendors

Vllm Vllm-project

Products

Vllm Vllm