CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-08 10:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

parallel : process system prompt once + configurable paramters + llama API

Browse Source
This commit is contained in:
Georgi Gerganov
2023-09-19 17:00:42 +03:00
parent 82e20e9ba0
commit 4b5f3cd6bf
9 changed files with 187 additions and 93 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
common/common.h
View File

@@ -43,6 +43,8 @@ struct gpt_params {
int32_t n_keep = 0; // number of tokens to keep from initial prompt
int32_t n_draft = 16; // number of tokens to draft during speculative decoding
int32_t n_chunks = -1; // max number of chunks to process (-1 = unlimited)
int32_t n_parallel = 1; // number of parallel sequences to decode
int32_t n_sequences = 1; // number of sequences to decode
int32_t n_gpu_layers = -1; // number of layers to store in VRAM (-1 - use default)
int32_t n_gpu_layers_draft = -1; // number of layers to store in VRAM for the draft model (-1 - use default)
int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors
@@ -108,6 +110,7 @@ struct gpt_params {
bool interactive_first = false; // wait for user input immediately
bool multiline_input = false; // reverse the usage of `\`
bool simple_io = false; // improves compatibility with subprocesses and limited consoles
bool hot_plug = false; // hot-plug new sequences for decoding
bool input_prefix_bos = false; // prefix BOS to user inputs, preceding input_prefix
bool ignore_eos = false; // ignore generated EOS tokens