Vllm
by Vllm
Source repositories
CVEs (145)
| 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… |
- 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…
Page 6 of 8