SamplerChain.sample

Sample the next token. batchIdx = -1 uses the last output position.

llama_token sample(llama_context* ctx, int batchIdx)
struct SamplerChain
@nogc nothrow
llama_token
sample
(
llama_context* ctx
,
int batchIdx = -1
)
llama_token sample(LlamaContext ctx, int batchIdx)

Meta

Source

See Implementation

llama sampling SamplerChain functions

mixins

__anonymous

static functions

create