nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add Hadamard parameters to draft model loading (#1840)

This commit is contained in:
Samuel Oliveira Alves 2026-05-19 12:30:41 -03:00 committed by GitHub
parent 997c587a6c
commit 77413bc900
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server-context.cpp
View File

@ -482,6 +482,8 @@ bool server_context::load_model(const gpt_params& params_) {
params_dft.cache_type_k = params_base.speculative.cache_type_k.empty() ? params_base.cache_type_k : params_base.speculative.cache_type_k;
params_dft.cache_type_v = params_base.speculative.cache_type_v.empty() ? params_base.cache_type_v : params_base.speculative.cache_type_v;
params_dft.flash_attn = params_base.flash_attn;
params_dft.k_cache_hadamard = params_base.k_cache_hadamard;
params_dft.v_cache_hadamard = params_base.v_cache_hadamard;
if (!params_base.speculative.params.empty()) {
auto [argc, argv] = parse_command_line("llama-server " + params_base.speculative.params);
if (!gpt_params_parse(argc, argv, params_dft)) {