happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

kv-cache : extend cache quantization checks (#21586) 

to also check for enabled flash attention, instead of just auto.
This commit is contained in:
Erik Scholz 2026-04-08 15:08:57 +02:00 committed by GitHub
parent 5473949070
commit 3ba12fed0a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-context.cpp
View File

@ -2942,7 +2942,7 @@ llama_context * llama_init_from_model(
params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_DISABLED;
}
if (params.flash_attn_type == LLAMA_FLASH_ATTN_TYPE_AUTO && ggml_is_quantized(params.type_k)) {
if (params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_DISABLED && ggml_is_quantized(params.type_k)) {
const uint32_t blck_size = ggml_blck_size(params.type_k);
for (uint32_t il = 0; il < model->hparams.n_layer; ++il) {
if (model->hparams.n_embd_head_k(il) % blck_size != 0) {
@ -2953,7 +2953,7 @@ llama_context * llama_init_from_model(
}
}
if (params.flash_attn_type == LLAMA_FLASH_ATTN_TYPE_AUTO && ggml_is_quantized(params.type_v)) {
if (params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_DISABLED && ggml_is_quantized(params.type_v)) {
const uint32_t blck_size = ggml_blck_size(params.type_v);
for (uint32_t il = 0; il < model->hparams.n_layer; ++il) {
if (model->hparams.n_embd_head_v(il) % blck_size != 0) {