CVE-2026-129356 | Medium | 5.0 | 2026-11-15 | A vulnerability was found in vllm-project vllm 0.30.0/0.31.0. This vulnerability affects unknown code of the file single_type_kv_cache_manager.py of the compon… |
CVE-2026-126399 | Medium | 6.5 | 2026-11-13 | vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion vulnerability that allows inference clients to bypass the server frame limit by setting media_io_… |
CVE-2026-126398 | Medium | 5.9 | 2026-11-13 | vLLM from 0.28.0 before 0.30.0 contains a reachable assertion vulnerability in GPUModelRunner._init_xdrope_positions that allows remote attackers to crash the… |
CVE-2026-126397 | High | 7.5 | 2026-11-13 | vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mm_processor_kwargs.max_patches value to the Hugging Face processor for Cohere2 Vision models with… |
CVE-2026-126396 | Medium | 5.3 | 2026-11-13 | vLLM from 0.24.0 before 0.31.0 contains a resource exhaustion vulnerability in the MiniMax M3 VL video processor, which accepts request-level min_pixels withou… |
CVE-2026-126395 | Medium | 5.3 | 2026-11-13 | vLLM from 0.14.0rc1 before 0.31.0 contains an information disclosure vulnerability in sanitize_message() whose lowercase-only regex fails to scrub uppercase PI… |
CVE-2026-126394 | Medium | 5.3 | 2026-11-13 | vLLM 0.30.0 before 0.31.0 contains a resource exhaustion vulnerability in OpenCVDynamicOpenPanguVideoBackend, which uses request-controlled num_frames without… |
CVE-2026-115918 | Medium | 6.5 | 2026-10-26 | 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… |
CVE-2026-115917 | Low | 3.4 | 2026-10-26 | vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allow… |
CVE-2026-115916 | Medium | 6.5 | 2026-10-26 | 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… |
CVE-2026-115915 | High | 8.1 | 2026-10-26 | 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… |
CVE-2026-115914 | Medium | 6.5 | 2026-10-26 | 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 all… |
CVE-2026-115913 | Medium | 6.5 | 2026-10-26 | 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 u… |
CVE-2026-115912 | High | 7.5 | 2026-10-26 | 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 monotoni… |
CVE-2026-115911 | Medium | 6.5 | 2026-10-26 | 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 s… |
CVE-2026-116181 | Medium | 6.5 | 2026-10-25 | 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-vocabul… |
CVE-2026-116180 | High | 7.7 | 2026-10-25 | 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… |
CVE-2026-116179 | High | 7.5 | 2026-10-25 | vLLM from 0.18.0 before 0.31.0 contains a resource exhaustion vulnerability that allows API clients to bypass the video/jpeg frame-count cap by overriding num_… |
CVE-2026-116178 | Medium | 5.9 | 2026-10-25 | 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 m… |
CVE-2026-116177 | High | 7.5 | 2026-10-25 | vLLM from 0.10.2 before 0.25.0 contains an uncontrolled resource consumption vulnerability that allows unauthenticated attackers to exhaust memory because the… |
CVE-2026-116176 | High | 8.2 | 2026-10-25 | 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… |
CVE-2026-116175 | Medium | 6.5 | 2026-10-25 | vLLM from 0.19.0 before 0.24.0 contains a decompression bomb vulnerability because the AudioMediaIO multimodal path calls load_audio without the max_duration_s… |
CVE-2026-116174 | Medium | 5.9 | 2026-10-25 | 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… |
CVE-2026-116173 | Medium | 5.9 | 2026-10-25 | 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 l… |
CVE-2026-116172 | Medium | 5.9 | 2026-10-25 | 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_logpro… |
CVE-2026-114055 | High | 7.5 | 2026-10-21 | vLLM from 0.7.3 before 0.31.0 contains an uncontrolled resource consumption vulnerability that allows remote clients to control multimodal processor parameters… |
CVE-2026-114054 | Medium | 6.5 | 2026-10-21 | vLLM before 0.31.0 contains a cache aliasing vulnerability that allows authenticated attackers to collide shared cache keys by supplying caller-controlled valu… |
CVE-2026-114053 | High | 8.1 | 2026-10-21 | 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 se… |
CVE-2026-114052 | High | 7.5 | 2026-10-21 | vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-c… |
CVE-2026-114051 | High | 7.5 | 2026-10-21 | 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 di… |
CVE-2026-114050 | High | 7.5 | 2026-10-21 | vLLM before 0.31.0 uses a client-supplied multimodal uuid verbatim as cache identity with no consistency check on cache hits, allowing engine crashes. Unauthen… |
CVE-2026-114049 | Low | 3.7 | 2026-10-21 | 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 stal… |
CVE-2026-109311 | Medium | 6.5 | 2026-10-12 | vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser heap overflow. Authen… |
CVE-2026-105922 | Medium | 4.3 | 2026-10-06 | A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file vllm/model_executor/… |
CVE-2026-105775 | Medium | 4.3 | 2026-10-06 | A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/model_executor/layers… |
CVE-2026-105760 | Medium | 5.3 | 2026-10-05 | vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMG… |
CVE-2026-105759 | Medium | 5.9 | 2026-10-05 | vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP meth… |
CVE-2026-105758 | Medium | 5.3 | 2026-10-05 | vLLM is an inference and serving engine for large language models. From 0.24.0 until 0.30.0, the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes accept req… |
CVE-2026-105757 | Medium | 6.5 | 2026-10-05 | vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and… |
CVE-2026-105756 | Medium | 6.5 | 2026-10-05 | vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value withou… |
CVE-2026-105755 | Medium | 4.2 | 2026-10-05 | vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives… |
CVE-2026-105754 | Medium | 6.5 | 2026-10-05 | vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path acc… |
CVE-2026-105753 | Medium | 6.5 | 2026-10-05 | vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a media hash in the fr… |
CVE-2026-105752 | Low | 3.1 | 2026-10-05 | vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/responses" requests… |
CVE-2026-103241 | Medium | 5.3 | 2026-09-30 | A flaw has been found in vllm-project vLLM up to 0.26.0. This vulnerability affects unknown code of the file rust/src/parser/src/unified/gemma4.rs of the compo… |
CVE-2026-100654 | Medium | 6.5 | 2026-09-26 | vLLM before 0.29.0 accepts user-controlled stop_token_ids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates o… |
CVE-2026-100653 | Medium | 6.5 | 2026-09-26 | vLLM is an inference and serving engine for large language models. In versions from 0.22.1 through 0.28.0, the operator-supplied model revision pin (--revision… |
CVE-2026-100652 | Medium | 5.9 | 2026-09-26 | 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… |
CVE-2026-100651 | Medium | 6.5 | 2026-09-26 | vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a… |
CVE-2026-100650 | Medium | 6.5 | 2026-09-26 | vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB c… |
CVE-2026-100649 | Low | 3.7 | 2026-09-26 | vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent coun… |
CVE-2026-100648 | Medium | 5.3 | 2026-09-26 | 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 si… |
CVE-2026-100647 | Medium | 5.3 | 2026-09-26 | vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter accepted on OpenAI-compatible and Anthropic API endpoints, wh… |
CVE-2026-94627 | High | 7.5 | 2026-09-21 | 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 prefi… |
CVE-2026-94626 | High | 7.5 | 2026-09-21 | vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints, allowing attackers to allocate unb… |
CVE-2026-94625 | Medium | 5.3 | 2026-09-21 | vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests create ownerless transfer placeholders th… |
CVE-2026-94624 | High | 7.5 | 2026-09-21 | vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a pee… |
CVE-2026-94623 | High | 7.5 | 2026-09-21 | 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 coun… |
CVE-2026-94622 | High | 7.5 | 2026-09-21 | vLLM versions through 0.29.0 contain a denial of service vulnerability in the NIXL connector's metadata handling for prefill/decode disaggregated deployments… |
CVE-2026-93989 | Low | 3.1 | 2026-09-19 | 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(). A… |
CVE-2026-93841 | Low | 3.7 | 2026-09-18 | 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 w… |
CVE-2026-93840 | Low | 3.7 | 2026-09-18 | vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). A… |
CVE-2026-93592 | High | 7.5 | 2026-09-18 | 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 c… |
CVE-2026-93436 | High | 7.5 | 2026-09-17 | vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attacke… |
CVE-2026-69147 | Medium | 6.5 | 2026-09-16 | vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.v… |
CVE-2026-57173 | Medium | 6.5 | 2026-09-16 | vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the input_audio handling path for /v1/chat/completions calls AudioMediaIO.l… |
CVE-2026-92365 | Medium | 4.3 | 2026-09-16 | A vulnerability was found in vllm-project vllm up to 0.29.0. Affected by this issue is some unknown functionality of the file vllm/v1/sample/thinking_budget_st… |
CVE-2026-92220 | Medium | 5.3 | 2026-09-16 | A vulnerability was found in vllm-project vLLM 0.26.0/0.27.0. Affected is the function MoRIIOConnectorScheduler.request_finished/MoRIIOConnectorWorker.get_fini… |
CVE-2026-90878 | Medium | 4.3 | 2026-09-15 | A vulnerability was determined in vllm-project vLLM up to 0.27.1. This affects an unknown part of the file /v1/chat/completions of the component Jinja Template… |
CVE-2026-90713 | Low | 3.3 | 2026-09-14 | A security flaw has been discovered in vllm-project vLLM up to 0.29.0. The affected element is the function TiktokenTokenizer::new of the file rust/src/text/sr… |
CVE-2026-90555 | Medium | 6.5 | 2026-09-12 | vLLM versions before 0.28.0 fail to validate audio sample rate headers in the transcription endpoint, allowing authenticated clients to bypass duration checks… |
CVE-2026-90554 | Medium | 6.2 | 2026-09-12 | 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 na… |
CVE-2026-90553 | High | 7.8 | 2026-09-12 | vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loa… |
CVE-2026-78684 | Medium | 5.3 | 2026-08-25 | 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 a… |
CVE-2026-73560 | Medium | 6.5 | 2026-08-17 | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformers_utils/processors/mim… |
CVE-2026-71486 | Medium | 4.3 | 2026-08-17 | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints ac… |
CVE-2026-73559 | Medium | 6.5 | 2026-08-13 | vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypo… |
CVE-2026-73558 | Medium | 5.3 | 2026-08-13 | vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can caus… |
CVE-2026-73557 | Medium | 5.3 | 2026-08-13 | vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safe_load_prompt_embeds in vllm/renderers/embed_utils.py uses t… |
CVE-2026-73556 | Medium | 5.3 | 2026-08-13 | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend… |
CVE-2026-73555 | Medium | 5.3 | 2026-08-13 | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the validation_exception_handler in vllm/entrypoints/openai/server_utils.py… |
CVE-2026-55574 | High | 7.5 | 2026-07-06 | 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… |
CVE-2026-55514 | Medium | 6.5 | 2026-07-06 | 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 u… |
CVE-2026-54234 | High | 7.5 | 2026-07-06 | 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 work… |
CVE-2026-55646 | Medium | 6.5 | 2026-07-06 | 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 r… |
CVE-2026-54236 | Medium | 5.3 | 2026-06-22 | 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 h… |
CVE-2026-54235 | Medium | 6.5 | 2026-06-22 | vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >)… |
CVE-2026-54233 | Medium | 6.5 | 2026-06-22 | 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… |
CVE-2026-54232 | High | 8.8 | 2026-06-22 | 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 t… |
CVE-2026-53923 | High | 7.5 | 2026-06-22 | 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 de… |
CVE-2026-48746 | Critical | 9.1 | 2026-06-22 | 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… |
CVE-2026-47155 | Medium | 6.5 | 2026-06-22 | 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 ar… |
CVE-2026-41523 | High | 7.5 | 2026-06-22 | 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… |
CVE-2026-12491 | Medium | 4.8 | 2026-06-17 | A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata, specif… |
CVE-2026-5497 | High | 7.5 | 2026-06-11 | 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 `VideoMedi… |
CVE-2026-4944 | High | 8.8 | 2026-05-28 | 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/mo… |
CVE-2026-9540 | Medium | 5.3 | 2026-05-26 | 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 ma… |
CVE-2026-44223 | Medium | 6.5 | 2026-05-12 | 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… |
CVE-2026-44222 | Medium | 6.5 | 2026-05-12 | 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 mul… |
CVE-2026-34756 | Medium | 6.5 | 2026-04-06 | 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 Ope… |