Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-10 23:09:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/nix/package.nix
#	.github/workflows/server.yml
#	docs/development/HOWTO-add-model.md
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/argsort-ops.c
#	ggml/src/ggml-hexagon/htp/concat-ops.c
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/gated-delta-net-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-ops.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/hvx-utils.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/pad-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-webgpu/wgsl-shaders/cpy.wgsl
#	scripts/sync_vendor.py
#	src/llama-context.cpp
#	tests/test-backend-sampler.cpp
#	tools/server/README.md
#	tools/ui/tests/stories/ChatScreenForm.a11y.stories.svelte
This commit is contained in:
Concedo
2026-06-02 19:28:39 +08:00
parent 153214c66a d5ab0834ab
commit 13eaa04269
78 changed files with 1801 additions and 477 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-kv-cache.cpp
+14 -2
View File
@@ -1885,7 +1885,19 @@ void llama_kv_cache::state_write(llama_io_write_i & io, llama_seq_id seq_id, lla
uint32_t cell_range_begin = cells.size();
for (uint32_t i = 0; i < cells.size(); ++i) {
if (!cells.is_empty(i) && (seq_id == -1 || cells.seq_has(i, seq_id))) {
bool add_cell = true;
add_cell = add_cell && !cells.is_empty(i);
add_cell = add_cell && (seq_id == -1 || cells.seq_has(i, seq_id));
// check the cell is not SWA-masked
if (add_cell && seq_id != -1) {
const bool is_masked = llama_hparams::is_masked_swa(n_swa, swa_type, cells.pos_get(i), cells.seq_pos_max(seq_id));
add_cell = !is_masked;
}
if (add_cell) {
++cell_count;
if (cell_range_begin == cells.size()) {
cell_range_begin = i;
@@ -2138,7 +2150,7 @@ bool llama_kv_cache::state_read_meta(llama_io_read_i & io, uint32_t strm, uint32
sinfo = find_slot(ubatch, false);
if (sinfo.empty()) {
LLAMA_LOG_ERROR("%s: failed to find available cells in kv cache\n", __func__);
LLAMA_LOG_ERROR("%s: failed to find %d available cells in kv cache\n", __func__, cell_count);
return false;
}