tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama_batch_ext_ptr::from_text/embd

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-14 17:12:03 +01:00
parent 8e7714fa77
commit eaffba0f2e
12 changed files with 34 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/speculative-simple/speculative-simple.cpp
View File

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