vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-12 05:52:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Merge commit '12280ae905' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	common/CMakeLists.txt
#	docs/docker.md
#	examples/model-conversion/scripts/causal/compare-logits.py
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	tests/test-backend-ops.cpp
#	tests/test-barrier.cpp
#	tools/server/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo 2025-12-16 16:29:01 +08:00
commit e88bf41fdc
49 changed files with 1380 additions and 583 deletions
Download patch file Download diff file Expand all files Collapse all files

5
src/llama-kv-cache.cpp
View file

@ -1232,8 +1232,7 @@ void llama_kv_cache::set_input_kq_mask(ggml_tensor * dst, const llama_ubatch * u
GGML_ASSERT(n_tokens%n_stream == 0);
// n_tps == n_tokens_per_stream
const int64_t n_tps = n_tokens/n_stream;
const int64_t n_tps_pad = GGML_PAD(n_tps, GGML_KQ_MASK_PAD);
const int64_t n_tps = n_tokens/n_stream;
std::fill(data, data + ggml_nelements(dst), -INFINITY);
@ -1266,7 +1265,7 @@ void llama_kv_cache::set_input_kq_mask(ggml_tensor * dst, const llama_ubatch * u
const llama_pos p1_x = is_2d ? ubatch->pos[i + ubatch->n_tokens*2] : 0;
const llama_pos p1_y = is_2d ? ubatch->pos[i + ubatch->n_tokens] : 0;
const uint64_t idst = n_kv*(h*n_stream*n_tps_pad + s*n_tps_pad + ii);
const uint64_t idst = n_kv*(h*n_stream*n_tps + s*n_tps + ii);
for (uint32_t j = 0; j < n_kv; ++j) {
if (cells.is_empty(j)) {