CVE-2026-114049

vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense that allows remote attackers to constrain other clients' outputs by leaving stale allowedtokenids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycl...

CVE-2026-114049 vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense

vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense that allows remote attackers to constrain other clients' outputs by leaving stale allowedtokenids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycl...

EUVD-2026-107000

vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense that allows remote attackers to constrain other clients' outputs by leaving stale allowedtokenids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycl...

CVE-2026-114049

Versions of vLLM prior to 0.31.0 are vulnerable to a cross-request mask leak within the InputBatch.condense() function. This flaw occurs because the application leaves stale allowed_token_ids rows, which can then be applied to subsequent requests. A remote attacker can exploit this by submitting ...

CVE-2026-114049

vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense that allows remote attackers to constrain other clients' outputs by leaving stale allowedtokenids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycl...

PT-2026-120175

vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense that allows remote attackers to constrain other clients' outputs by leaving stale allowed token ids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so...