vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-14 00:01:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/musa.Dockerfile
#	.github/workflows/build.yml
#	README.md
#	ci/README.md
#	docs/docker.md
#	examples/lookahead/lookahead.cpp
#	examples/lookup/lookup.cpp
#	examples/parallel/parallel.cpp
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tests/test-arg-parser.cpp
This commit is contained in:
Concedo 2025-05-21 23:12:22 +08:00
commit da7fd4aa57
22 changed files with 270 additions and 384 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/llama-graph.cpp
View file

@ -1368,6 +1368,10 @@ ggml_tensor * llm_graph_context::build_attn(
if (wo) {
cur = build_lora_mm(wo, cur);
if (arch == LLM_ARCH_GLM4) {
// GLM4 seems to have numerical issues with half-precision accumulators
ggml_mul_mat_set_prec(cur, GGML_PREC_F32);
}
}
if (wo_b) {