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

server : fix speculative decoding with context shift

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2024-12-03 22:44:19 +02:00
parent cc98896db8
commit a5a915b51e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@ -2325,7 +2325,7 @@ struct server_context {
llama_token id = slot.sampled; llama_token id = slot.sampled;
struct common_speculative_params params_spec; struct common_speculative_params params_spec;
params_spec.n_draft = slot.params.speculative.n_max; params_spec.n_draft = std::min(slot.params.speculative.n_max, slot.n_ctx - slot.n_past - 1);
params_spec.n_reuse = llama_n_ctx(slot.ctx_dft) - slot.params.speculative.n_max; params_spec.n_reuse = llama_n_ctx(slot.ctx_dft) - slot.params.speculative.n_max;
params_spec.p_min = slot.params.speculative.p_min; params_spec.p_min = slot.params.speculative.p_min;