vllm.config.watermarking ¶
Classes:
-
WatermarkConfig–Configuration for text watermark generation.
WatermarkConfig ¶
Configuration for text watermark generation.
Attributes:
-
algorithm(WatermarkingAlgorithm) –Algorithm used to watermark generated text.
-
allow_target_only_watermarking(bool) –Allow speculative decoding without watermarking draft tokens.
-
alpha(float) –Probability of selecting key B for dual-key watermarking.
-
context_width(int) –Number of prior tokens used by the watermark PRF.
-
deduplicate_contexts(WatermarkContextScope) –Which history is searched for a repeated context before a token is
-
deduplicate_contexts_max_history(int | None) –Number of most recent history positions searched (default 8192), or
-
key(int) –Secret key used to watermark generated text.
-
prf(WatermarkPRFName) –Pseudorandom function used by the watermarking algorithm.
Source code in vllm/config/watermarking.py
algorithm = 'gumbel' class-attribute instance-attribute ¶
Algorithm used to watermark generated text.
allow_target_only_watermarking = False class-attribute instance-attribute ¶
Allow speculative decoding without watermarking draft tokens.
alpha = Field(default=0.1, ge=0, le=1) class-attribute instance-attribute ¶
Probability of selecting key B for dual-key watermarking.
context_width = Field(default=4, ge=1) class-attribute instance-attribute ¶
Number of prior tokens used by the watermark PRF.
deduplicate_contexts = 'single_turn' class-attribute instance-attribute ¶
Which history is searched for a repeated context before a token is sampled; a repeated context is sampled without the watermark. none disables the search. single_turn (default) searches this request's generated tokens. all also searches the prompt and samples the first context_width generated tokens without watermarking.
deduplicate_contexts_max_history = Field(default=8192, ge=1) class-attribute instance-attribute ¶
Number of most recent history positions searched (default 8192), or None for the whole scope. Each position is compared over the context_width tokens before it. Ignored when deduplicate_contexts is none.
key = Field(ge=0, repr=False, exclude=True) class-attribute instance-attribute ¶
Secret key used to watermark generated text.
prf = 'philox' class-attribute instance-attribute ¶
Pseudorandom function used by the watermarking algorithm.