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

llama_decode_ext

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-02-24 17:01:20 +01:00
parent aed4a8e980
commit 4bf7ca3943
3 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/server.cpp
View File

@@ -3149,7 +3149,7 @@ struct server_context {
llama_batch_ext_ptr batch_view(llama_batch_ext_get_view(batch.get(), i, n_tokens));
const int ret = llama_text_decode(ctx, batch_view.get());
const int ret = llama_decode_ext(ctx, batch_view.get());
metrics.on_decoded(slots);
if (ret != 0) {
@@ -3294,7 +3294,7 @@ struct server_context {
SLT_DBG(slot, "decoding speculative batch, size = %d\n", llama_batch_ext_get_n_tokens(slot.batch_spec.get()));
llama_text_decode(ctx, slot.batch_spec.get());
llama_decode_ext(ctx, slot.batch_spec.get());
// the accepted tokens from the speculation
const auto ids = common_sampler_sample_and_accept_n(slot.smpl, ctx, draft);