vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-14 19:09:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

memory : handle kv_unified for hybrid models (#15050)

Browse source
This commit is contained in:
compilade 2025-08-03 15:43:07 -04:00 • committed by GitHub
parent 97366dc6ab
commit 11a3811164
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
src/llama-memory-hybrid.cpp
View file

@ -25,6 +25,7 @@ llama_memory_hybrid::llama_memory_hybrid(
/* common */
uint32_t n_seq_max,
bool offload,
bool unified,
/* layer filters */
layer_filter_cb && filter_attn,
layer_filter_cb && filter_recr) :
@ -38,7 +39,7 @@ llama_memory_hybrid::llama_memory_hybrid(
type_v,
v_trans,
offload,
1,
unified,
kv_size,
n_seq_max,
n_pad,