GHSA-85XF-C7HM-WHQW vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites)

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back each path reaches. Summary Three structured-output request paths let an ordinary request reach a condition...

vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites)

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back each path reaches. Summary Three structured-output request paths let an ordinary request reach a condition...

EUVD-2026-92847

vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service 3 sites...

GHSA-2823-QMQ8-RWVJ vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the loose cachesalt validator and unguarded scheduling-path lookup reach. Summary vLLM's OpenAI-compatible...

vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the loose cachesalt validator and unguarded scheduling-path lookup reach. Summary vLLM's OpenAI-compatible...

PYSEC-2026-4199

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by t...

CVE-2026-105757

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by t...

CVE-2026-105757 vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites)

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by t...

CVE-2026-105757

The vLLM inference and serving engine for large language models is vulnerable to a denial of service (DoS) condition in versions prior to 0.30.0 . The root cause is that structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. Specific tri...

CVE-2026-105757 vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites)

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by t...

CVE-2026-105757 vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites)

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by t...

CVE-2026-105756 vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cachesalt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the...

CVE-2026-105756 vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cachesalt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the...

CVE-2026-105756 vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cachesalt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the...

CVE-2026-105756

Prior to version 0.30.0 , the vLLM inference and serving engine is vulnerable to a denial of service via an uncaught ValueError . The root cause is improper input validation of the cache_salt value in OpenAI-compatible request models. On deployments using the LMCache-MP connector, providing a sal...

CVE-2026-105754

The vLLM inference and serving engine (prior to version 0.30.0 ) contains a vulnerability in the /inference/v1/generate endpoint within the disaggregated scale-out path. The root cause is that the system trusts caller-supplied features—specifically in the features.kwargs_data , features.mm_hashes...

CVE-2026-105754 vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargsdata field, cache identifiers in the features.mmhashes field, ranges in the...

CVE-2026-105754: Improper Input Validation

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargsdata field, cache identifiers in the features.mmhashes field, ranges in the...

CVE-2026-105757: Improper Input Validation

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by t...

PYSEC-2026-4185

vLLM versions 0.22.0 through 0.23.0 fail to validate stoptokenids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with mintokens greater than zero and out-of-vocabulary stoptokenids to...