Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 08:44:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '12280ae9058600b0b14335fe59848e601e10eebc' 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
parent 78bbe89956 12280ae905
commit e88bf41fdc
49 changed files with 1380 additions and 583 deletions
Download Patch File Download Diff File Expand all files Collapse all files
otherarch/whispercpp/whisper.cpp
+2 -2
View File
@@ -2378,7 +2378,7 @@ static struct ggml_cgraph * whisper_build_graph_decoder(
const float KQscale = pow(float(n_state_head), -0.25);
struct ggml_tensor * KQ_mask = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_kv, GGML_PAD(n_tokens, GGML_KQ_MASK_PAD), 1);
struct ggml_tensor * KQ_mask = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_kv, GGML_PAD(n_tokens, 1), 1);
ggml_set_name(KQ_mask, "KQ_mask");
ggml_set_input(KQ_mask);
@@ -2806,7 +2806,7 @@ static bool whisper_decode_internal(
}
}
for (int i = n_tokens; i < GGML_PAD(n_tokens, GGML_KQ_MASK_PAD); ++i) {
for (int i = n_tokens; i < GGML_PAD(n_tokens, 1); ++i) {
for (int j = 0; j < n_kv; ++j) {
data[h*(n_kv*n_tokens) + i*n_kv + j] = -INFINITY;
}