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 commit '34df42f7bef5a711b2b40f5d2b6b78254def99c3' into concedo_experimental

Browse Source 
# Conflicts:
#	README.md
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/binary-ops.c
#	ggml/src/ggml-hexagon/htp/cpy-ops.c
#	ggml/src/ggml-hexagon/htp/get-rows-ops.c
#	ggml/src/ggml-hexagon/htp/htp-msg.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-arith.h
#	ggml/src/ggml-hexagon/htp/hvx-base.h
#	ggml/src/ggml-hexagon/htp/hvx-inverse.h
#	ggml/src/ggml-hexagon/htp/hvx-utils.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	ggml/src/ggml-hexagon/htp/set-rows-ops.c
#	ggml/src/ggml-hexagon/htp/softmax-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	tests/test-backend-ops.cpp
#	tools/cli/cli.cpp
#	tools/server/webui/src/lib/components/app/chat/ChatScreen/ChatScreen.svelte
This commit is contained in:
Concedo
2026-03-10 22:20:04 +08:00
parent 746664fde6 34df42f7be
commit 6adcd0b5db
168 changed files with 15852 additions and 1398 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-kv-cache.cpp
+12 -2
View File
@@ -1760,8 +1760,10 @@ void llama_kv_cache::state_write_meta(llama_io_write_i & io, const cell_ranges_t
io.write(&pos, sizeof(pos));
io.write(&n_seq_id, sizeof(n_seq_id));
// TODO: we also need to save llama_kv_cell_ext when apply_ubatch() support loading it
// see: https://github.com/ggml-org/llama.cpp/pull/16825#issuecomment-3460868350
if (hparams.n_pos_per_embd() > 1) {
const llama_kv_cell_ext ext = cells.ext_get(i);
io.write(&ext, sizeof(ext));
}
for (const auto & seq_id : seq_ids) {
io.write(&seq_id, sizeof(seq_id));
@@ -1895,6 +1897,14 @@ bool llama_kv_cache::state_read_meta(llama_io_read_i & io, uint32_t strm, uint32
return false;
}
if (hparams.n_pos_per_embd() > 1) {
llama_kv_cell_ext ext;
io.read_to(&ext, sizeof(ext));
ubatch.pos[i + ubatch.n_tokens] = ext.y;
ubatch.pos[i + ubatch.n_tokens*2] = ext.x;
}
// read the sequence id, but directly discard it - we will use dest_seq_id instead
{
llama_seq_id seq_id;