furyhawk/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-21 10:15:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

spec : fix naming, spacing (#25410)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-07-07 18:52:30 +03:00
committed by GitHub
parent 3899b39ce2
commit c198af4dc2
3 changed files with 20 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-context.cpp
+7 -6
View File
@@ -900,7 +900,7 @@ private:
llama_model * model_dft = nullptr;
llama_context * ctx_dft = nullptr;
common_init_speculative_result_ptr spec_init;
common_speculative_init_result_ptr spec_init;
common_context_seq_rm_type ctx_tgt_seq_rm_type = COMMON_CONTEXT_SEQ_RM_TYPE_NO;
common_context_seq_rm_type ctx_dft_seq_rm_type = COMMON_CONTEXT_SEQ_RM_TYPE_NO;
@@ -1171,11 +1171,12 @@ private:
{
common_params params_dft = common_base_params_to_speculative(params_base);
// progress callback
params_dft.load_progress_callback = load_progress_callback;
params_dft.load_progress_callback_user_data = &load_progress_spec;
spec_init = common_init_speculative_from_params(params_dft, model_tgt, ctx_tgt);
spec_init = common_speculative_init_from_params(params_dft, model_tgt, ctx_tgt);
model_dft = spec_init->model();
ctx_dft = spec_init->context();
@@ -2306,8 +2307,8 @@ private:
// this is not true for SWA models: https://github.com/ggml-org/llama.cpp/pull/24411#issuecomment-4677983225
cur.update_pos(slot.prompt.n_tokens() - n_tokens_cur, pos_min, pos_max);
cur.update_tgt(ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
cur.update_dft(ctx_dft, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
cur.update_tgt(ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
cur.update_dft(ctx_dft, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
// stash the draft's speculative state with the checkpoint
common_speculative_get_state(spec.get(), slot.id, cur.data_spec);
@@ -3264,8 +3265,8 @@ private:
if (!do_reset) {
// restore the context checkpoint
it->load_tgt(ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
it->load_dft(ctx_dft, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
it->load_tgt(ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
it->load_dft(ctx_dft, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
// restore the draft's speculative state
common_speculative_set_state(spec.get(), slot.id, it->data_spec);