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

llama : more consistent names of count variables (#5994)

Browse source 
* llama : more consistent names of count variables

ggml-ci

* llama : n_parallel -> n_seq_max

* common : fix param name

* examples : fix param name
This commit is contained in:
Georgi Gerganov 2024-03-11 17:49:47 +02:00 • committed by GitHub
parent 83796e62bc
commit 05b06210c9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 35 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama.h
View file

@ -235,7 +235,7 @@ extern "C" {
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_parallel; // number of parallel sequences (i.e. distinct states for recurrent models)
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
@ -377,7 +377,7 @@ 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_max_seq (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);
LLAMA_API enum llama_rope_type llama_rope_type (const struct llama_model * model);
@ -456,7 +456,7 @@ extern "C" {
// Maximum number of sequences that can exist in a cell. It's not an error
// if there are more sequences in a cell than this value, however they will
// not be visible in the view cells_sequences.
int32_t n_max_seq;
int32_t n_seq_max;
// Number of tokens in the cache. For example, if there are two populated
// cells, the first with 1 sequence id in it and the second with 2 sequence
@ -476,12 +476,12 @@ extern "C" {
// Information for an individual cell.
struct llama_kv_cache_view_cell * cells;
// The sequences for each cell. There will be n_max_seq items per cell.
// The sequences for each cell. There will be n_seq_max items per cell.
llama_seq_id * cells_sequences;
};
// Create an empty KV cache view. (use only for debugging purposes)
LLAMA_API struct llama_kv_cache_view llama_kv_cache_view_init(const struct llama_context * ctx, int32_t n_max_seq);
LLAMA_API struct llama_kv_cache_view llama_kv_cache_view_init(const struct llama_context * ctx, int32_t n_seq_max);
// Free a KV cache view. (use only for debugging purposes)
LLAMA_API void llama_kv_cache_view_free(struct llama_kv_cache_view * view);
@ -708,7 +708,7 @@ extern "C" {
/// @details Convert the provided text into tokens.
/// @param tokens The tokens pointer must be large enough to hold the resulting tokens.
/// @return Returns the number of tokens on success, no more than n_max_tokens
/// @return Returns the number of tokens on success, no more than n_tokens_max
/// @return Returns a negative number on failure - the number of tokens that would have been returned
/// @param special Allow tokenizing special and/or control tokens which otherwise are not exposed and treated as plaintext.
/// Does not insert a leading space.
@ -717,7 +717,7 @@ extern "C" {
const char * text,
int32_t text_len,
llama_token * tokens,
int32_t n_max_tokens,
int32_t n_tokens_max,
bool add_bos,
bool special);