CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

compile ok

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-13 22:56:35 +01:00
parent 9fb2d81eab
commit 65f0184517
9 changed files with 46 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/speculative-simple/speculative-simple.cpp
View File

@@ -113,7 +113,8 @@ int main(int argc, char ** argv) {
struct common_sampler * smpl = common_sampler_init(model_tgt, params.sampling);
// eval the prompt
llama_decode(ctx_tgt, llama_batch_get_one(inp.data(), inp.size() - 1));
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(inp.data(), inp.size() - 1, 0, 0));
llama_decode_ext(ctx_tgt, batch.get());
// note: keep the last token separate!
llama_token id_last = inp.back();