nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

server : disable on-device spec checkpoints (#24108)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-06-04 19:30:59 +03:00
committed by GitHub
parent 260862b8ca
commit 7c158fbb4a
2 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
examples/speculative-simple/speculative-simple.cpp
View File

@@ -175,7 +175,7 @@ int main(int argc, char ** argv) {
llama_memory_seq_pos_max(llama_get_memory(ctx_tgt), seq_id));
if (use_ckpt_dft) {
ckpt.update_dft(ctx_dft.get(), seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE);
ckpt.update_dft(ctx_dft.get(), seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
}
// generate a new draft
@@ -196,12 +196,12 @@ int main(int argc, char ** argv) {
// this allows us to restore the state if partial draft acceptance occurs
if (!draft.empty()) {
if (use_ckpt_tgt) {
ckpt.update_tgt(ctx_tgt, seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE);
ckpt.update_tgt(ctx_tgt, seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
}
}
{
ckpt.load_dft(ctx_dft.get(), seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE);
ckpt.load_dft(ctx_dft.get(), seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
llama_memory_seq_rm(llama_get_memory(ctx_dft.get()), seq_id, ckpt.pos_max + 1, -1);
}
@@ -261,13 +261,13 @@ int main(int argc, char ** argv) {
draft = std::move(ids);
{
ckpt.load_tgt(ctx_tgt, seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE);
ckpt.load_tgt(ctx_tgt, seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
llama_memory_seq_rm(llama_get_memory(ctx_tgt), seq_id, ckpt.pos_max + 1, -1);
}
{
ckpt.load_dft(ctx_dft.get(), seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY | LLAMA_STATE_SEQ_FLAGS_ON_DEVICE);
ckpt.load_dft(ctx_dft.get(), seq_id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
llama_memory_seq_rm(llama_get_memory(ctx_dft.get()), seq_id, ckpt.pos_max + 1, -1);
}