thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

kv-cache : fix SWA checks + disable cacheless iSWA (#15811)

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2025-09-05 10:39:22 +03:00 • committed by GitHub
parent 5d6688de08
commit c610b6c11b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 29 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-hparams.cpp
View file

@ -180,7 +180,7 @@ uint32_t llama_hparams::n_layer_kv() const {
return res;
}
bool llama_hparams::is_masked_swa(llama_pos p0, llama_pos p1) const {
bool llama_hparams::is_masked_swa(uint32_t n_swa, llama_swa_type swa_type, llama_pos p0, llama_pos p1) {
assert(p0 >= 0 && p1 >= 0);
switch (swa_type) {