vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-30 12:03:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

server: MTP layer kv-cache should respect draft type ctk (#23646)

Browse source
This commit is contained in:
Aman Gupta 2026-05-25 16:46:23 +08:00 • committed by GitHub
parent 5fdf07e33b
commit 6c4cbdc70b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tools/server/server-context.cpp
View file

@ -822,6 +822,8 @@ private:
auto cparams_dft = common_context_params_to_llama(params_dft);
if (spec_mtp) {
cparams_dft.ctx_type = LLAMA_CONTEXT_TYPE_MTP;
cparams_dft.type_k = params_base.speculative.draft.cache_type_k;
cparams_dft.type_v = params_base.speculative.draft.cache_type_v;
}
cparams_dft.n_rs_seq = 0;
@ -940,6 +942,8 @@ private:
auto cparams_mtp = common_context_params_to_llama(params_base);
cparams_mtp.ctx_type = LLAMA_CONTEXT_TYPE_MTP;
cparams_mtp.type_k = params_base.speculative.draft.cache_type_k;
cparams_mtp.type_v = params_base.speculative.draft.cache_type_v;
cparams_mtp.n_rs_seq = 0;
ctx_dft.reset(llama_init_from_model(model_tgt, cparams_mtp));