llama-cpp-d ~master (2026-03-20T18:06:26.5280947)

batchGetOne

llama batch

Wraps a token slice into a batch. The slice must outlive the returned batch.

  1. llama_batch batchGetOne(const(llama_token)[] tokens)
    @trusted @nogc nothrow
    llama_batch
    batchGetOne
    (
    scope const(llama_token)[] tokens
    )
  2. llama_batch batchGetOne(llama_token* tokens, int nTokens)

Meta

Source

See Implementation

llama batch functionsstructs

Page generated by adrdox