Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

default kv_unified to true, handle LLAMA_SET_ROWS.

Browse Source
This commit is contained in:
Concedo
2025-07-21 16:13:20 +08:00
parent 30675b0798
commit 6d50def409
5 changed files with 18 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
otherarch/tts_adapter.cpp
+1
View File
@@ -539,6 +539,7 @@ bool ttstype_load_model(const tts_load_model_inputs inputs)
tts_ctx_params.n_threads = nthreads;
tts_ctx_params.n_threads_batch = nthreads;
tts_ctx_params.flash_attn = inputs.flash_attention;
tts_ctx_params.kv_unified = true;
llama_model * ttcmodel = llama_model_load_from_file(modelfile_ttc.c_str(), tts_model_params);
ttc_ctx = llama_init_from_model(ttcmodel, tts_ctx_params);