Lucene search
+L

792 matches found

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.50 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
ATTACKERKB
ATTACKERKB
added 2026/08/13 3:09 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...

6.5CVSS5.3AI score0.00472EPSS
SaveExploits0References5Affected Software1
EUVD
EUVD
added 2026/08/13 3:09 p.m.14 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
CVE
CVE
added 2026/08/13 3:09 p.m.69 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
Cvelist
Cvelist
added 2026/08/13 3:09 p.m.36 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.77 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.36 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.10 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
OSV
OSV
added 2026/08/13 3:06 p.m.34 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...

5.3CVSS5.5AI score
SaveExploits0References7
CVE
CVE
added 2026/08/13 3:00 p.m.52 views

CVE-2026-73557

CVE-2026-73557 affects vLLM between 0.20.2rc0 and 0.26.0. The flaw arises in safe_load_prompt_embeds in vllm/renderers/embed_utils.py, where using torch.sparse.check_sparse_tensor_invariants with a process-global save/enable/restore state can be raced via concurrent prompt_embeds (POST /v1/chat/c...

6.3CVSS5.3AI score0.00251EPSS
SaveExploits0References4
OSV
OSV
added 2026/08/13 3:00 p.m.24 views

CVE-2026-73557 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

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...

6.3CVSS5.4AI score
SaveExploits0References6
ATTACKERKB
ATTACKERKB
added 2026/08/13 3:00 p.m.18 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...

6.3CVSS5.3AI score0.00251EPSS
SaveExploits0References5Affected Software1
Cvelist
Cvelist
added 2026/08/13 3:00 p.m.49 views

CVE-2026-73557 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

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
CVE
CVE
added 2026/08/13 2:56 p.m.31 views

CVE-2026-73556

vLLM before 0.26.0 is affected by a DoS-like issue in the lm-format-enforcer backend: structured_outputs.regex is passed to RegexParser without compile_timeout or validation in validate_structured_output_request_lm_format_enforcer, allowing unauthenticated /v1/completions requests to consume CPU ...

5.3CVSS5.3AI score0.00315EPSS
SaveExploits0References4
ATTACKERKB
ATTACKERKB
added 2026/08/13 2:56 p.m.10 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...

5.3CVSS5.3AI score0.00315EPSS
SaveExploits0References5Affected Software1
Rows per page
Query Builder