upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-06 18:10:51 -05:00
Code Issues Packages Projects Releases Wiki Activity

speculative : add tree-based sampling support

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2023-10-14 17:54:02 +03:00
parent 5261aee8d8
commit 4de5a2d473
11 changed files with 469 additions and 192 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/simple/simple.cpp
View File

@@ -92,7 +92,7 @@ int main(int argc, char ** argv) {
// create a llama_batch with size 512
// we use this object to submit token data for decoding
llama_batch batch = llama_batch_init(512, 0);
llama_batch batch = llama_batch_init(512, 0, 1);
// evaluate the initial prompt
batch.n_tokens = tokens_list.size();