Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	docs/development/HOWTO-add-model.md
#	docs/multimodal.md
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/gated_delta_net.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/upscale.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	tests/test-backend-ops.cpp
#	tests/test-llama-archs.cpp
#	tools/mtmd/CMakeLists.txt
This commit is contained in:
Concedo
2026-04-14 20:06:04 +08:00
parent 0c65244dad 75f3bc94e6
commit 9c0b9b0bb1
53 changed files with 3214 additions and 720 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/mtmd-helper.cpp
+3 -2
View File
@@ -274,7 +274,8 @@ int32_t mtmd_helper_decode_image_chunk(
batch_embd.set_position_normal(n_past, seq_id);
}
if (mtmd_decode_use_non_causal(ctx)) {
const bool use_non_causal = mtmd_decode_use_non_causal(ctx, chunk);
if (use_non_causal) {
llama_set_causal_attn(lctx, false);
// TODO @ngxson : need to make sure only one image is processed at a time, and n_ubatch must be enough to hold the image
}
@@ -302,7 +303,7 @@ int32_t mtmd_helper_decode_image_chunk(
n_past += mtmd_input_chunk_get_n_pos(chunk);
*new_n_past = n_past;
if (mtmd_decode_use_non_causal(ctx)) {
if (use_non_causal) {
llama_set_causal_attn(lctx, true);
}
return 0;