VLLM: Responses API Bypasses Trust_request_chat_template For Chat_template_kwargs

Summary vLLM's "/v1/responses" endpoint accepts request-level "chattemplatekwargs", but does not apply the "--trust-request-chat-template" gate that protects Chat Completions, render, tokenize, and pooling paths. When the server is run with the documented default "trustrequestchattemplate=False"...

vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs

Summary vLLM's /v1/responses endpoint accepts request-level chattemplatekwargs, but does not apply the --trust-request-chat-template gate that protects Chat Completions, render, tokenize, and pooling paths. When the server is run with the documented default trustrequestchattemplate=False and no...

EUVD-2026-110039

vLLM: Responses API bypasses trustrequestchattemplate for chattemplatekwargs...

GHSA-X567-49G5-P4CF vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs

Summary vLLM's /v1/responses endpoint accepts request-level chattemplatekwargs, but does not apply the --trust-request-chat-template gate that protects Chat Completions, render, tokenize, and pooling paths. When the server is run with the documented default trustrequestchattemplate=False and no...

SUSE CVE-2026-115918

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

Allocation of Resources Without Limits or Throttling

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling via the chat template rendering path in the Responses API endpoint, where a request-supplied...

PYSEC-2026-4349

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

CVE-2026-115918

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

PYSEC-2026-4349

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

CVE-2026-115918 vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

CVE-2026-115918 vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

CVE-2026-115918

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

vLLM resource management error vulnerability

Versions vLLM 0.16.0 through 0.31.0 contain a resource management error vulnerability. This vulnerability arises because the /v1/responses endpoint permits authenticated callers to place attacker-controlled templates via chattemplatekwargschattemplate when no server template is configured; it fai...

vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server

SummaryA resource-exhaustion denial-of-service vulnerability exists in multiple endpoints of the OpenAI-Compatible Server due to the ability to specify Jinja templates via the chattemplate and chattemplatekwargs parameters. If an attacker can supply these parameters to the API, they can cause a...

CVE-2025-62426 vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chattemplatekwargs request parameter that is used in the code before it is properly validated against the chat template. With the...

CVE-2025-62426

vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chattemplatekwargs request parameter that is used in the code before it is properly validated against the chat template. With the...

CVE-2025-62426: Allocation of Resources Without Limits or Throttling

vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chattemplatekwargs request parameter that is used in the code before it is properly validated against the chat template. With the...