CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-05 09:36:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : improve llama_batch API + simplify parallel example

Browse Source
This commit is contained in:
Georgi Gerganov
2023-09-20 10:46:18 +03:00
parent a1327c71c6
commit addae65fd4
6 changed files with 111 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/speculative/speculative.cpp
View File

@@ -134,7 +134,7 @@ int main(int argc, char ** argv) {
while (true) {
// sample from the target model
const llama_token id = llama_sample_token(ctx_tgt, NULL, grammar_tgt, params, last_tokens, candidates, i_dft);
llama_token id = llama_sample_token(ctx_tgt, NULL, grammar_tgt, params, last_tokens, candidates, i_dft);
// remember which tokens were sampled - used for repetition penalties during sampling
last_tokens.erase(last_tokens.begin());