diff options
Diffstat (limited to 'llama.h')
| -rw-r--r-- | llama.h | 9 |
1 files changed, 8 insertions, 1 deletions
@@ -234,7 +234,8 @@ extern "C" { struct llama_context_params { uint32_t seed; // RNG seed, -1 for random uint32_t n_ctx; // text context, 0 = from model - uint32_t n_batch; // prompt processing maximum batch size + uint32_t n_batch; // logical maximum batch size that can be submitted to llama_decode + uint32_t n_ubatch; // physical maximum batch size uint32_t n_seq_max; // max number of sequences (i.e. distinct states for recurrent models) uint32_t n_threads; // number of threads to use for generation uint32_t n_threads_batch; // number of threads to use for batch processing @@ -377,6 +378,7 @@ extern "C" { LLAMA_API uint32_t llama_n_ctx (const struct llama_context * ctx); LLAMA_API uint32_t llama_n_batch (const struct llama_context * ctx); + LLAMA_API uint32_t llama_n_ubatch (const struct llama_context * ctx); LLAMA_API uint32_t llama_n_seq_max (const struct llama_context * ctx); LLAMA_API enum llama_vocab_type llama_vocab_type(const struct llama_model * model); @@ -650,6 +652,11 @@ extern "C" { // Set abort callback LLAMA_API void llama_set_abort_callback(struct llama_context * ctx, ggml_abort_callback abort_callback, void * abort_callback_data); + // Wait until all computations are finished + // This is automatically done when using one of the functions below to obtain the computation results + // and is not necessary to call it explicitly in most cases + LLAMA_API void llama_synchronize(struct llama_context * ctx); + // Token logits obtained from the last call to llama_decode() // The logits for the last token are stored in the last row // Logits for which llama_batch.logits[i] == 0 are undefined |