Lucene search
+L

756 matches found

RedhatCVE
RedhatCVE
added 2026/08/14 3:24 p.m.11 views

CVE-2026-73555

A flaw was found in vLLM, an inference and serving engine for large language models. Unauthenticated attackers can send malformed JSON requests to various API endpoints, triggering validation errors. The system's error handling mechanism converts these validation errors into strings without...

5.3CVSS5.4AI score0.00255EPSS
SaveExploits0References7
RedhatCVE
RedhatCVE
added 2026/08/14 3:24 p.m.9 views

CVE-2026-73557

A flaw was found in vLLM, an inference and serving engine for large language models. An incomplete remediation for a previous vulnerability CVE-2025-62164 can be bypassed. This occurs when concurrent prompt parts are processed, leading to a race condition in the handling of sparse tensors. This...

6.3CVSS5.4AI score0.00251EPSS
SaveExploits0References7
RedhatCVE
RedhatCVE
added 2026/08/14 3:23 p.m.14 views

CVE-2026-73558

A flaw was found in vLLM, an inference and serving engine for large language models. An integer overflow vulnerability in the actandmulkernel kernel allows a remote attacker to cause cross-user data leakage. By crafting specific requests processed in the same inference batch, an attacker can obta...

5.3CVSS5.5AI score0.00326EPSS
SaveExploits0References8
RedhatCVE
RedhatCVE
added 2026/08/14 3:20 p.m.12 views

CVE-2026-73559

A flaw was found in vLLM, an inference and serving engine for large language models. An authenticated API client can exploit this vulnerability by sending a single request to the /v1/completions endpoint with an excessively large list of prompts. This unbounded input causes the vLLM server to...

6.5CVSS5.5AI score0.00472EPSS
SaveExploits0References7
RedhatCVE
RedhatCVE
added 2026/08/14 3:20 p.m.12 views

CVE-2026-73556

A flaw was found in vLLM, an inference and serving engine for large language models. An unauthenticated remote attacker can exploit a Regular Expression Denial of Service ReDoS vulnerability in the lm-format-enforcer backend. By submitting a specially crafted regular expression through the...

7.5CVSS5.5AI score0.00315EPSS
SaveExploits0References7
Github Security Blog
Github Security Blog
added 2026/08/13 6:40 p.m.19 views

vLLM: Completion prompt lists fan out into unbounded engine requests

Summary The /v1/completions request model accepts prompt as a list of text prompts or a list of token-id prompts without any outer prompt-count bound. The serving path turns each element into a separate engine input, creates one engine generator per element, merges all generators, and allocates a...

6.5CVSS5.7AI score0.00472EPSS
SaveExploits0References6Affected Software1
OSV
OSV
added 2026/08/13 6:40 p.m.16 views

GHSA-87X5-VMC3-756J vLLM: Completion prompt lists fan out into unbounded engine requests

Summary The /v1/completions request model accepts prompt as a list of text prompts or a list of token-id prompts without any outer prompt-count bound. The serving path turns each element into a separate engine input, creates one engine generator per element, merges all generators, and allocates a...

6.5CVSS5.8AI score0.00472EPSS
SaveExploits0References6
NVD
NVD
added 2026/08/13 4:19 p.m.9 views

CVE-2026-73559

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/entrypoints/openai/completion/protocol.py accepts an unbounded liststr or listlistint, prompttoseq in vllm/renderers/inputs/preprocess.py and...

6.5CVSS0.00472EPSS
SaveExploits0References4
NVD
NVD
added 2026/08/13 3:20 p.m.11 views

CVE-2026-73558

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 activationkernels.cu can cause actandmulkernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or...

5.3CVSS0.00326EPSS
SaveExploits0References5
NVD
NVD
added 2026/08/13 3:20 p.m.12 views

CVE-2026-73557

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...

6.3CVSS0.00251EPSS
SaveExploits0References4
NVD
NVD
added 2026/08/13 3:20 p.m.10 views

CVE-2026-73555

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the validationexceptionhandler in vllm/entrypoints/openai/serverutils.py converts FastAPI RequestValidationError objects with strexc, and sanitizemessage in vllm/entrypoints/utils.py does not remove traceback-styl...

5.3CVSS0.00255EPSS
SaveExploits0References4
NVD
NVD
added 2026/08/13 3:20 p.m.9 views

CVE-2026-73556

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structuredoutputs.regex parameter in vllm/v1/structuredoutput/backendlmformatenforcer.py is passed to lmformatenforcer.RegexParser without compileregexwithtimeout or validation in...

5.3CVSS0.00315EPSS
SaveExploits0References4
OSV
OSV
added 2026/08/13 3:09 p.m.47 views

CVE-2026-73559 vLLM: Completion prompt lists fan out into unbounded engine requests

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/entrypoints/openai/completion/protocol.py accepts an unbounded liststr or listlistint, prompttoseq in vllm/renderers/inputs/preprocess.py and...

6.5CVSS5.4AI score
SaveExploits0References6
CVE
CVE
added 2026/08/13 3:09 p.m.67 views

CVE-2026-73559

CVE-2026-73559 affects vLLM (0.19.0–0.26.0) where the /v1/completions prompt field can be an unbounded list, and prompt_to_seq/remove expansion in preprocessing may spawn unbounded expansion and create one engine generator/response slot per prompt. This can exhaust CPU, memory, async scheduling c...

6.5CVSS5.3AI score0.00472EPSS
SaveExploits0References4
ATTACKERKB
ATTACKERKB
added 2026/08/13 3:09 p.m.8 views

CVE-2026-73559

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/entrypoints/openai/completion/protocol.py accepts an unbounded liststr or listlistint, prompttoseq in vllm/renderers/inputs/preprocess.py and...

6.5CVSS5.3AI score0.00472EPSS
SaveExploits0References5Affected Software1
EUVD
EUVD
added 2026/08/13 3:09 p.m.13 views

EUVD-2026-58067

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/entrypoints/openai/completion/protocol.py accepts an unbounded liststr or listlistint, prompttoseq in vllm/renderers/inputs/preprocess.py and...

6.5CVSS5.3AI score0.00472EPSS
SaveExploits0References4
Cvelist
Cvelist
added 2026/08/13 3:09 p.m.35 views

CVE-2026-73559 vLLM: Completion prompt lists fan out into unbounded engine requests

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/entrypoints/openai/completion/protocol.py accepts an unbounded liststr or listlistint, prompttoseq in vllm/renderers/inputs/preprocess.py and...

6.5CVSS0.00472EPSS
SaveExploits0References4
CVE
CVE
added 2026/08/13 3:06 p.m.72 views

CVE-2026-73558

The CVE concerns vLLM, an inference/serving engine for LLMs. Before version 0.27.0, an integer overflow in blockIdx.x * 2 * d within activation_kernels.cu enables act_and_mul_kernel to consume input from another user within the same inference batch, causing cross-user data leakage of partial or c...

5.3CVSS5.4AI score0.00326EPSS
SaveExploits0References5
Cvelist
Cvelist
added 2026/08/13 3:06 p.m.35 views

CVE-2026-73558 vLLM: Cross-User Data Leak Vulnerability

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 activationkernels.cu can cause actandmulkernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or...

5.3CVSS0.00326EPSS
SaveExploits0References5
ATTACKERKB
ATTACKERKB
added 2026/08/13 3:06 p.m.9 views

CVE-2026-73558

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 activationkernels.cu can cause actandmulkernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or...

5.3CVSS5.3AI score0.00326EPSS
SaveExploits0References6Affected Software1
Rows per page
Query Builder