Skip to content
CVE
by OpenHack
Browse
All CVEs
Every CVE, newest first, with filters
CVEs by company
Microsoft, Cisco, Fortinet and 840 more
CVEs by package
Open-source packages on npm, PyPI, Maven, Go…
Critical
About
Search CVEs, products, packages and vendors
/
Packages
PyPI
vllm
vllm CVEs
PyPI package
Search CVEs, products, packages and vendors
Severity
Any
Published
All time
Exploited only
Version
Clear
113 CVEs
·
5 without a fix
·
CVE
Record
Severity
Status
Published
CVE-2026-100652
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. A
Fixed in 0.24.0
High
7.5
Fix available
Sep 26
CVE-2026-100650
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 compressed-audio size cap, default 25 MB,
Fixed in 0.30.0
Unrated
Fix available
Sep 26
CVE-2026-94626
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 unbounded memory. Attackers can supply arbit
Fixed in 0.30.0
Unrated
Fix available
Sep 21
CVE-2026-94625
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 sen
Fixed in 0.30.0
Unrated
Fix available
Sep 21
CVE-2026-94623
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 request
Fixed in 0.30.0
Unrated
Fix available
Sep 21
CVE-2026-94622
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 incomple
Fixed in 0.30.0
Unrated
Fix available
Sep 21
CVE-2026-93989
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 i
Fixed in 0.30.0
Medium
4.3
Fix available
Sep 19
CVE-2026-93841
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
Fixed in 0.30.0
Medium
5.3
Fix available
Sep 18
CVE-2026-93840
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 o
Fixed in 0.29.0
Medium
5.3
Fix available
Sep 18
CVE-2026-93592
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 to
Fixed in 0.28.0
Unrated
Fix available
Sep 18
CVE-2026-93436
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
Fixed in 0.30.0
Unrated
Fix available
Sep 17
CVE-2026-69147
vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation
Fixed in 0.28.0
Medium
6.5
Fix available
Sep 17
CVE-2026-57173
vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions
Fixed in 0.24.0
Medium
6.5
Fix available
Sep 16
CVE-2026-90553
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
Fixed in 0.28.0
Unrated
Fix available
Sep 12
CVE-2026-73560
vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections
Fixed in 0.26.0
Medium
6.5
Fix available
Sep 8
CVE-2026-73558
vLLM: Cross-User Data Leak Vulnerability
Fixed in 0.27.0
Medium
5.3
Fix available
Sep 8
CVE-2026-73557
vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts
Fixed in 0.26.0
Medium
Fix available
Sep 4
CVE-2026-73556
vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile timeout) — missed sibling of GHSA-rwxx-mrjm-wc2m
Fixed in 0.26.0
Medium
5.3
Fix available
Sep 4
CVE-2026-73555
vLLM: Unauthenticated Internal Path and Username Disclosure via Validation Error Messages
Fixed in 0.26.0
Medium
5.3
Fix available
Sep 4
CVE-2026-71486
vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds
Fixed in 0.26.0
Medium
4.3
Fix available
Sep 4
CVE-2026-78684
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 ini
Fixed in 0.27.0
Unrated
Fix available
Aug 25
CVE-2026-73559
vLLM: Completion prompt lists fan out into unbounded engine requests
Fixed in 0.26.0
Medium
6.5
Fix available
Aug 13
CVE-2026-55514
vLLM denial of service via prompt embeds on M-RoPE models
Fixed in 0.24.0
High
Fix available
Jul 20
CVE-2026-55646
vLLM: Speech-to-text upload size limit is enforced after full UploadFile read
Fixed in 0.24.0
Medium
6.5
Fix available
Jul 17
CVE-2026-55574
vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends
Fixed in 0.24.0
High
7.5
Fix available
Jul 17
CVE-2026-54234
vLLM has Remote DoS via Invalid Recovered Token Reinjection
Fixed in 0.24.0
High
7.5
Fix available
Jul 17
CVE-2026-34760
vLLM: Processing differential in multi-channel audio downmixing enables hidden-input/moderation bypass for audio models
Fixed in 0.18.0
Medium
5.9
Fix available
Jul 17
CVE-2026-54232
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 through the flashinfer-jit-cache package.
Fixed in 0.22.1
High
8.8
Fix available
Jun 22
CVE-2026-54233
vLLM: OOM Denial of Service via Audio Decompression Bomb
Fixed in 0.24.0
Medium
6.5
Fix available
Jun 17
CVE-2026-54236
vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router
Fixed in 0.24.0
Medium
5.3
Fix available
Jun 17
Showing
31–60
of 113
Previous
1
2
3
4
Next