[feature] Watermarked generation and detection (Gumbel-max algorithm) (#54053)

Signed-off-by: Raphael Rialland <raphael.rialland@mistral.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Raphaël Rialland
2026-09-09 21:00:15 -07:00
committed by GitHub
co-authored by OpenAI Codex mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 8c34a37232
commit ea40bb9e90
32 changed files with 1693 additions and 15 deletions
@@ -0,0 +1,32 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
from vllm.entrypoints.openai.completion.protocol import CompletionRequest
from vllm.entrypoints.openai.responses.protocol import ResponsesRequest
def test_chat_request_disables_watermarking():
request = ChatCompletionRequest(
messages=[{"role": "user", "content": "hello"}], watermarking=False
)
params = request.to_sampling_params(max_tokens=1, default_sampling_params={})
assert not params.watermarking
def test_completion_request_disables_watermarking():
request = CompletionRequest(prompt="hello", watermarking=False)
params = request.to_sampling_params(max_tokens=1)
assert not params.watermarking
def test_responses_request_disables_watermarking():
request = ResponsesRequest(input="hello", watermarking=False)
params = request.to_sampling_params(default_max_tokens=1)
assert not params.watermarking