Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-09 06:19:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-webgpu.yml
#	CMakeLists.txt
#	common/CMakeLists.txt
#	docs/development/HOWTO-add-model.md
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/CMakeLists.txt
#	tests/test-arg-parser.cpp
#	tests/test-jinja.cpp
#	tests/test-llama-archs.cpp
#	tests/test-save-load-state.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo
2026-07-27 22:28:38 +08:00
parent 90510f2b27 0324696b8e
commit fee0bf446c
74 changed files with 2516 additions and 361 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+5 -3
View File
@@ -2348,7 +2348,8 @@ uint32_t llama_context::graph_max_nodes(uint32_t n_tokens) const {
model.arch == LLM_ARCH_KIMI_LINEAR ||
model.arch == LLM_ARCH_QWEN35 ||
model.arch == LLM_ARCH_QWEN35MOE ||
model.arch == LLM_ARCH_DEEPSEEK4) {
model.arch == LLM_ARCH_DEEPSEEK4 ||
model.arch == LLM_ARCH_MINIMAX_M3) {
return std::max<uint32_t>(n_tokens * 40, 32u * model.n_tensors());
}
uint32_t res = std::max<uint32_t>(1024u, 8u*model.n_tensors());
@@ -2482,11 +2483,12 @@ llm_graph_cb llama_context::graph_get_cb() const {
ggml_set_name(cur, name);
}
// norm may be automatically assigned to the backend of the previous layer, increasing data transfer between backends
// - norm may be automatically assigned to the backend of the previous layer, increasing data transfer between backends
// - force the last op of the layer on the specified backend to avoid running it on the backend of the next layer due to scheduling
// FIXME: fix in ggml_backend_sched
const bool full_offload = model.n_gpu_layers() > model.hparams.n_layer_all;
if (ubatch.n_tokens < 32 || full_offload) {
if (il != -1 && strcmp(name, "norm") == 0) {
if (il != -1 && (strcmp(name, "norm") == 0 || strcmp(name, "l_last") == 0)) {
const auto & dev_layer = model.dev_layer(il);
for (const auto & backend : backends) {
if (ggml_backend_get_device(backend.get()) == dev_layer) {