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

llama : refactor sampling v2 (#9294)

Browse source 
- Add `struct llama_sampler` and `struct llama_sampler_i`
- Add `llama_sampler_` API
- Add `llama_sampler_chain_` API for chaining multiple samplers
- Remove `LLAMA_API_INTERNAL`
- Add `llama_perf_` API and remove old `llama_print_timings` and `llama_reset_timings`
This commit is contained in:
Georgi Gerganov 2024-09-07 15:16:19 +03:00 • committed by GitHub
parent 947538acb8
commit df270ef745
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
48 changed files with 3497 additions and 2914 deletions
Download patch file Download diff file Expand all files Collapse all files

6
common/common.h
View file

@ -77,8 +77,6 @@ struct cpu_params {
};
struct gpt_params {
uint32_t seed = LLAMA_DEFAULT_SEED; // RNG seed
int32_t n_predict = -1; // new tokens to predict
int32_t n_ctx = 0; // context size
int32_t n_batch = 2048; // logical batch size for prompt processing (must be >=32 to use BLAS)
@ -120,8 +118,7 @@ struct gpt_params {
enum llama_pooling_type pooling_type = LLAMA_POOLING_TYPE_UNSPECIFIED; // pooling type for embeddings
enum llama_attention_type attention_type = LLAMA_ATTENTION_TYPE_UNSPECIFIED; // attention type for embeddings
// // sampling parameters
struct llama_sampling_params sparams;
struct gpt_sampler_params sparams;
std::string model = ""; // model path
std::string model_draft = ""; // draft model for speculative decoding
@ -185,7 +182,6 @@ struct gpt_params {
bool flash_attn = false; // flash attention
bool input_prefix_bos = false; // prefix BOS to user inputs, preceding input_prefix
bool ignore_eos = false; // ignore generated EOS tokens
bool logits_all = false; // return logits for all tokens in the batch
bool use_mmap = true; // use mmap for faster loads
bool use_mlock = false; // use mlock to keep model in memory