Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/labeler.yml
#	.github/workflows/release.yml
#	examples/debug/debug.cpp
#	ggml/src/ggml-cuda/common.cuh
#	ggml/src/ggml-cuda/mmq.cuh
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	src/llama-vocab.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tools/mtmd/CMakeLists.txt
This commit is contained in:
Concedo
2026-04-09 17:45:04 +08:00
parent 5529748a01 d12cc3d1ca
commit c82c0b463a
76 changed files with 1232 additions and 10766 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+2 -2
View File
@@ -2952,7 +2952,7 @@ 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) {
@@ -2963,7 +2963,7 @@ 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) {