SUSE CVE-2026-93840

vLLM before 0.29.0 validates allowedtokenids against tokenizer length instead of model output logits width in SamplingParams.validateallowedtokenids. Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow...

EUVD-2026-83617

vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...

CVE-2026-93989

vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...

CVE-2026-93989 vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words

vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...

CVE-2026-93989 vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words

vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...

CVE-2026-93989 vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words

vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...

PYSEC-2026-3998

vLLM before 0.29.0 validates allowedtokenids against tokenizer length instead of model output logits width in SamplingParams.validateallowedtokenids. Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow...

PYSEC-0000-CVE-2026-93840

vLLM before 0.29.0 validates allowedtokenids against tokenizer length instead of model output logits width in SamplingParams.validateallowedtokenids. Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow...

CVE-2026-93840 vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids

vLLM before 0.29.0 validates allowedtokenids against tokenizer length instead of model output logits width in SamplingParams.validateallowedtokenids. Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow...

CVE-2026-93840 vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids

vLLM before 0.29.0 validates allowedtokenids against tokenizer length instead of model output logits width in SamplingParams.validateallowedtokenids. Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow...

CVE-2026-93840

vLLM before 0.29.0 is vulnerable to cross-request logits corruption via the allowed_token_ids parameter. The root cause is in SamplingParams._validate_allowed_token_ids() , which validates token IDs against the tokenizer length rather than the model output logits width. An attacker can supply tok...

PT-2026-102784

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 output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow...

CVE-2026-93840: Improper Validation of Array Index

vLLM before 0.29.0 validates allowedtokenids against tokenizer length instead of model output logits width in SamplingParams.validateallowedtokenids. Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow...