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

Merge branch 'master' into compilade/bitnet-ternary

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-09-04 13:26:50 -04:00
commit 7f3a619c98
94 changed files with 12171 additions and 7726 deletions
Download patch file Download diff file Expand all files Collapse all files

24
include/llama.h
View file

@ -66,6 +66,7 @@ extern "C" {
LLAMA_VOCAB_TYPE_BPE = 2, // GPT-2 tokenizer based on byte-level BPE
LLAMA_VOCAB_TYPE_WPM = 3, // BERT tokenizer based on WordPiece
LLAMA_VOCAB_TYPE_UGM = 4, // T5 tokenizer based on Unigram
LLAMA_VOCAB_TYPE_RWKV = 5, // RWKV tokenizer based on greedy tokenization
};
// pre-tokenization types
@ -269,9 +270,9 @@ extern "C" {
enum llama_split_mode split_mode; // how to split the model across multiple GPUs
// main_gpu interpretation depends on split_mode:
// LLAMA_SPLIT_NONE: the GPU that is used for the entire model
// LLAMA_SPLIT_ROW: the GPU that is used for small tensors and intermediate results
// LLAMA_SPLIT_LAYER: ignored
// LLAMA_SPLIT_MODE_NONE: the GPU that is used for the entire model
// LLAMA_SPLIT_MODE_ROW: the GPU that is used for small tensors and intermediate results
// LLAMA_SPLIT_MODE_LAYER: ignored
int32_t main_gpu;
// proportion of the model (layers or rows) to offload to each GPU, size: llama_max_devices()
@ -306,8 +307,8 @@ extern "C" {
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
int32_t n_threads; // number of threads to use for generation
int32_t n_threads_batch; // number of threads to use for batch processing
enum llama_rope_scaling_type rope_scaling_type; // RoPE scaling type, from `enum llama_rope_scaling_type`
enum llama_pooling_type pooling_type; // whether to pool (sum) embedding results by sequence id
@ -430,6 +431,13 @@ extern "C" {
//optional:
LLAMA_API void llama_numa_init(enum ggml_numa_strategy numa);
// Optional: an auto threadpool gets created in ggml if not passed explicitly
LLAMA_API void llama_attach_threadpool(
struct llama_context * ctx,
ggml_threadpool_t threadpool,
ggml_threadpool_t threadpool_batch);
LLAMA_API void llama_detach_threadpool(struct llama_context * ctx);
// Call once at the end of the program - currently only used for MPI
LLAMA_API void llama_backend_free(void);
@ -839,13 +847,13 @@ extern "C" {
// Set the number of threads used for decoding
// n_threads is the number of threads used for generation (single token)
// n_threads_batch is the number of threads used for prompt and batch processing (multiple tokens)
LLAMA_API void llama_set_n_threads(struct llama_context * ctx, uint32_t n_threads, uint32_t n_threads_batch);
LLAMA_API void llama_set_n_threads(struct llama_context * ctx, int32_t n_threads, int32_t n_threads_batch);
// Get the number of threads used for generation of a single token.
LLAMA_API uint32_t llama_n_threads(struct llama_context * ctx);
LLAMA_API int32_t llama_n_threads(struct llama_context * ctx);
// Get the number of threads used for prompt and batch processing (multiple token).
LLAMA_API uint32_t llama_n_threads_batch(struct llama_context * ctx);
LLAMA_API int32_t llama_n_threads_batch(struct llama_context * ctx);
// Set whether the model is in embeddings mode or not
// If true, embeddings will be returned but logits will not