vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into compilade/refactor-kv-cache

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-07-04 17:33:52 -04:00
commit 9b38f8bf65
102 changed files with 4745 additions and 1675 deletions
Download patch file Download diff file Expand all files Collapse all files

16
include/llama.h
View file

@ -89,6 +89,7 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_SMAUG = 14,
LLAMA_VOCAB_PRE_TYPE_PORO = 15,
LLAMA_VOCAB_PRE_TYPE_VIKING = 16,
LLAMA_VOCAB_PRE_TYPE_JAIS = 17,
};
// note: these values should be synchronized with ggml_rope
@ -484,6 +485,13 @@ extern "C" {
// Get a llama model tensor
LLAMA_API struct ggml_tensor * llama_get_model_tensor(struct llama_model * model, const char * name);
// Returns true if the model contains an encoder that requires llama_encode() call
LLAMA_API bool llama_model_has_encoder(const struct llama_model * model);
// For encoder-decoder models, this function returns id of the token that must be provided
// to the decoder to start generating output sequence. For other models, it returns -1.
LLAMA_API llama_token llama_model_decoder_start_token(const struct llama_model * model);
// Returns 0 on success
LLAMA_API uint32_t llama_model_quantize(
const char * fname_inp,
@ -819,6 +827,14 @@ extern "C" {
// Frees a batch of tokens allocated with llama_batch_init()
LLAMA_API void llama_batch_free(struct llama_batch batch);
// Processes a batch of tokens with the ecoder part of the encoder-decoder model.
// Stores the encoder output internally for later use by the decoder cross-attention layers.
// 0 - success
// < 0 - error
LLAMA_API int32_t llama_encode(
struct llama_context * ctx,
struct llama_batch batch);
// Positive return values does not mean a fatal error, but rather a warning.
// 0 - success
// 1 - could not find a KV slot for the batch (try reducing the size of the batch or increase the context)