Vendor CVEs
Vllm
All CVEs
146 total · sorted by risk| CVE | Vendor / Product | Sev | Risk | CVSS | EPSS | KEV | Published | Description |
|---|---|---|---|---|---|---|---|---|
| CVE-2026-129356 | Med | 0.33 | 5.0 | 0.00 | Nov 15, 2026 | 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 component Common Prefix Handler. The manipulation results in race condition. The attack may be performed from remote. Attacks… | ||
| CVE-2026-90554 | Med | 0.33 | 6.2 | 0.00 | Sep 12, 2026 | 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… | ||
| CVE-2026-116178 | Med | 0.31 | 5.9 | 0.00 | Oct 25, 2026 | 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… | ||
| CVE-2026-116174 | Med | 0.31 | 5.9 | 0.00 | Oct 25, 2026 | 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… | ||
| CVE-2026-116173 | Med | 0.31 | 5.9 | 0.00 | Oct 25, 2026 | 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… | ||
| CVE-2026-116172 | Med | 0.31 | 5.9 | 0.00 | Oct 25, 2026 | 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… | ||
| CVE-2026-105759 | Med | 0.31 | 5.9 | 0.00 | Oct 5, 2026 | 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 method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker can send unique… | ||
| CVE-2026-100652 | Med | 0.31 | 5.9 | 0.00 | Sep 26, 2026 | 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… | ||
| CVE-2026-34760 | Med | 0.31 | 5.9 | 0.00 | Apr 2, 2026 | 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.… | ||
| CVE-2026-7141 | Med | 0.29 | 5.6 | 0.00 | Apr 27, 2026 | 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… | ||
| CVE-2026-105922 | Med | 0.28 | 4.3 | 0.00 | Oct 6, 2026 | 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/layers/utils.py of the component Penalty Handler. Performing a manipulation results in denial of service. Remote… | ||
| CVE-2026-105775 | Med | 0.28 | 4.3 | 0.00 | Oct 6, 2026 | 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/mamba/mamba_mixer2.py of the component Completions Request Handler. The manipulation leads to out-of-bounds read. The… | ||
| CVE-2026-103241 | Med | 0.28 | 5.3 | 0.01 | Sep 30, 2026 | 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 component Gemma4UnifiedParser. Executing a manipulation can lead to denial of service. The attack may be launched remotely.… | ||
| CVE-2026-54236 | Med | 0.28 | 5.3 | 0.01 | Jun 22, 2026 | 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… | ||
| CVE-2026-34753 | Med | 0.28 | 5.4 | 0.00 | Apr 6, 2026 | 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… | ||
| CVE-2026-105760 | Med | 0.27 | 5.3 | 0.00 | Oct 5, 2026 | 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 GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA… | ||
| CVE-2026-105758 | Med | 0.27 | 5.3 | 0.00 | Oct 5, 2026 | 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 request-level values for the media_io_kwargs.video.max_frames and media_io_kwargs.video.fps fields without enforcing… | ||
| CVE-2026-100648 | Med | 0.27 | 5.3 | 0.00 | Sep 26, 2026 | 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… | ||
| CVE-2026-100647 | Med | 0.27 | 5.3 | 0.00 | Sep 26, 2026 | 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, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated… | ||
| CVE-2026-94625 | Med | 0.27 | 5.3 | 0.01 | Sep 21, 2026 | 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… | ||
| CVE-2026-92220 | Med | 0.27 | 5.3 | 0.01 | Sep 16, 2026 | A vulnerability was found in vllm-project vLLM 0.26.0/0.27.0. Affected is the function MoRIIOConnectorScheduler.request_finished/MoRIIOConnectorWorker.get_finished/MoRIIOWrapper._handle_release_message of the file vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_connect… | ||
| CVE-2026-78684 | Med | 0.27 | 5.3 | 0.01 | Aug 25, 2026 | 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… | ||
| CVE-2026-73558 | Med | 0.27 | 5.3 | 0.00 | Aug 13, 2026 | 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 cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch… | ||
| CVE-2026-73557 | Med | 0.27 | 5.3 | 0.00 | Aug 13, 2026 | 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 torch.sparse.check_sparse_tensor_invariants, whose process-global save, enable, and restore state can be raced by… | ||
| CVE-2026-73556 | Med | 0.27 | 5.3 | 0.01 | Aug 13, 2026 | 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_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in… | ||
| CVE-2026-73555 | Med | 0.27 | 5.3 | 0.00 | Aug 13, 2026 | 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 converts FastAPI RequestValidationError objects with str(exc), and sanitize_message in vllm/entrypoints/utils.py does… | ||
| CVE-2026-12491 | Med | 0.24 | 4.8 | 0.00 | Jun 17, 2026 | A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata, specifically EXIF orientation and PNG transparency (tRNS) data, during image processing. When images are converted to RGB,… | ||
| CVE-2026-92365 | Med | 0.21 | 4.3 | 0.01 | Sep 16, 2026 | 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_state.py. The manipulation results in inefficient algorithmic complexity. It is possible to launch the attack remotely.… | ||
| CVE-2026-90878 | Med | 0.21 | 4.3 | 0.01 | Sep 15, 2026 | 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 Rendering. This manipulation of the argument chat_template causes resource consumption. The attack can be initiated… | ||
| CVE-2026-71486 | Med | 0.21 | 4.3 | 0.00 | Aug 17, 2026 | 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 accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs,… | ||
| CVE-2025-71379 | Med | 0.21 | 4.3 | 0.00 | Jun 20, 2026 | vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic… | ||
| CVE-2026-105755 | Med | 0.20 | 4.2 | 0.00 | Oct 5, 2026 | 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 each worker's query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a… | ||
| CVE-2025-46722 | Med | 0.20 | 4.2 | 0.00 | May 29, 2025 | vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it… | ||
| CVE-2025-61620 | med | 0.19 | — | 0.00 | Oct 7, 2025 | ### Summary A resource-exhaustion (denial-of-service) vulnerability exists in multiple endpoints of the OpenAI-Compatible Server due to the ability to specify Jinja templates via the `chat_template` and `chat_template_kwargs` parameters. If an attacker can supply these… | ||
| CVE-2026-114049 | Low | 0.17 | 3.7 | 0.00 | Oct 21, 2026 | 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… | ||
| CVE-2026-100649 | Low | 0.17 | 3.7 | 0.00 | Sep 26, 2026 | vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent counter increments. Unauthenticated attackers can select different sampler subclasses in video requests to exceed configured… | ||
| CVE-2026-93841 | Low | 0.17 | 3.7 | 0.00 | Sep 18, 2026 | 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… | ||
| CVE-2026-93840 | Low | 0.17 | 3.7 | 0.00 | Sep 18, 2026 | 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… | ||
| CVE-2025-1953 | Low | 0.17 | 2.6 | 0.00 | Mar 4, 2025 | A vulnerability has been found in vLLM AIBrix 0.2.0 and classified as problematic. Affected by this vulnerability is an unknown functionality of the file pkg/plugins/gateway/prefixcacheindexer/hash.go of the component Prefix Caching. The manipulation leads to insufficiently… | ||
| CVE-2026-115917 | Low | 0.15 | 3.4 | 0.00 | Oct 26, 2026 | 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… | ||
| CVE-2026-90713 | Low | 0.14 | 3.3 | 0.00 | Sep 14, 2026 | 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/src/backend/hf/mod.rs of the component tiktoken vocab File Handler. The manipulation results in denial of service. The… | ||
| CVE-2026-105752 | Low | 0.13 | 3.1 | 0.00 | Oct 5, 2026 | 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 rebuild the next-turn engine input without preserving the cache_salt value, placing the continuation prefix in the… | ||
| CVE-2026-93989 | Low | 0.13 | 3.1 | 0.00 | Sep 19, 2026 | 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… | ||
| CVE-2025-46570 | Low | 0.10 | 2.6 | 0.00 | May 29, 2025 | vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token).… | ||
| CVE-2025-25183 | Low | 0.10 | 2.6 | 0.00 | Feb 7, 2025 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use… | ||
| CVE-2024-9052 | 0.00 | — | — | Mar 20, 2025 | Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority. |
- risk 0.33cvss 5.0epss 0.00
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 component Common Prefix Handler. The manipulation results in race condition. The attack may be performed from remote. Attacks…
- risk 0.33cvss 6.2epss 0.00
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…
- risk 0.31cvss 5.9epss 0.00
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…
- risk 0.31cvss 5.9epss 0.00
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…
- risk 0.31cvss 5.9epss 0.00
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…
- risk 0.31cvss 5.9epss 0.00
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…
- risk 0.31cvss 5.9epss 0.00
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 method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker can send unique…
- risk 0.31cvss 5.9epss 0.00
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…
- risk 0.31cvss 5.9epss 0.00
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.…
- risk 0.29cvss 5.6epss 0.00
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…
- risk 0.28cvss 4.3epss 0.00
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/layers/utils.py of the component Penalty Handler. Performing a manipulation results in denial of service. Remote…
- risk 0.28cvss 4.3epss 0.00
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/mamba/mamba_mixer2.py of the component Completions Request Handler. The manipulation leads to out-of-bounds read. The…
- risk 0.28cvss 5.3epss 0.01
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 component Gemma4UnifiedParser. Executing a manipulation can lead to denial of service. The attack may be launched remotely.…
- risk 0.28cvss 5.3epss 0.01
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…
- risk 0.28cvss 5.4epss 0.00
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…
- risk 0.27cvss 5.3epss 0.00
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 GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA…
- risk 0.27cvss 5.3epss 0.00
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 request-level values for the media_io_kwargs.video.max_frames and media_io_kwargs.video.fps fields without enforcing…
- risk 0.27cvss 5.3epss 0.00
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…
- risk 0.27cvss 5.3epss 0.00
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, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated…
- risk 0.27cvss 5.3epss 0.01
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…
- risk 0.27cvss 5.3epss 0.01
A vulnerability was found in vllm-project vLLM 0.26.0/0.27.0. Affected is the function MoRIIOConnectorScheduler.request_finished/MoRIIOConnectorWorker.get_finished/MoRIIOWrapper._handle_release_message of the file vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_connect…
- risk 0.27cvss 5.3epss 0.01
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…
- risk 0.27cvss 5.3epss 0.00
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 cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch…
- risk 0.27cvss 5.3epss 0.00
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 torch.sparse.check_sparse_tensor_invariants, whose process-global save, enable, and restore state can be raced by…
- risk 0.27cvss 5.3epss 0.01
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_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in…
- risk 0.27cvss 5.3epss 0.00
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 converts FastAPI RequestValidationError objects with str(exc), and sanitize_message in vllm/entrypoints/utils.py does…
- risk 0.24cvss 4.8epss 0.00
A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata, specifically EXIF orientation and PNG transparency (tRNS) data, during image processing. When images are converted to RGB,…
- risk 0.21cvss 4.3epss 0.01
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_state.py. The manipulation results in inefficient algorithmic complexity. It is possible to launch the attack remotely.…
- risk 0.21cvss 4.3epss 0.01
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 Rendering. This manipulation of the argument chat_template causes resource consumption. The attack can be initiated…
- risk 0.21cvss 4.3epss 0.00
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 accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs,…
- risk 0.21cvss 4.3epss 0.00
vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic…
- risk 0.20cvss 4.2epss 0.00
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 each worker's query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a…
- risk 0.20cvss 4.2epss 0.00
vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it…
- risk 0.19cvss —epss 0.00
### Summary A resource-exhaustion (denial-of-service) vulnerability exists in multiple endpoints of the OpenAI-Compatible Server due to the ability to specify Jinja templates via the `chat_template` and `chat_template_kwargs` parameters. If an attacker can supply these…
- risk 0.17cvss 3.7epss 0.00
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…
- risk 0.17cvss 3.7epss 0.00
vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent counter increments. Unauthenticated attackers can select different sampler subclasses in video requests to exceed configured…
- risk 0.17cvss 3.7epss 0.00
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…
- risk 0.17cvss 3.7epss 0.00
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…
- risk 0.17cvss 2.6epss 0.00
A vulnerability has been found in vLLM AIBrix 0.2.0 and classified as problematic. Affected by this vulnerability is an unknown functionality of the file pkg/plugins/gateway/prefixcacheindexer/hash.go of the component Prefix Caching. The manipulation leads to insufficiently…
- risk 0.15cvss 3.4epss 0.00
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…
- risk 0.14cvss 3.3epss 0.00
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/src/backend/hf/mod.rs of the component tiktoken vocab File Handler. The manipulation results in denial of service. The…
- risk 0.13cvss 3.1epss 0.00
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 rebuild the next-turn engine input without preserving the cache_salt value, placing the continuation prefix in the…
- risk 0.13cvss 3.1epss 0.00
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…
- risk 0.10cvss 2.6epss 0.00
vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token).…
- risk 0.10cvss 2.6epss 0.00
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use…
- CVE-2024-9052Mar 20, 2025risk 0.00cvss —epss —
Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority.
Page 3 of 3