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

4
src/llama-kv-cache-iswa.cpp
View file

@ -60,14 +60,14 @@ llama_kv_cache_iswa::llama_kv_cache_iswa(
kv_base = std::make_unique<llama_kv_cache>(
model, type_k, type_v,
v_trans, offload, unified, size_base, n_seq_max, n_pad,
0, filter_base, reuse);
0, LLAMA_SWA_TYPE_NONE, filter_base, reuse);
LLAMA_LOG_INFO("%s: creating SWA KV cache, size = %u cells\n", __func__, size_swa);
kv_swa = std::make_unique<llama_kv_cache>(
model, type_k, type_v,
v_trans, offload, unified, size_swa, n_seq_max, n_pad,
hparams.n_swa, filter_swa, reuse);
hparams.n_swa, hparams.swa_type, filter_swa, reuse);
}
void llama_kv_cache_iswa::clear(bool data) {