Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-06 13:01:21 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '34af94cd9ab277632e27caeec2d41de2fd091b31' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/docker.yml
#	.github/workflows/make-release.yml
#	.github/workflows/release.yml
#	.pi/gg/SYSTEM.md
#	CMakeLists.txt
#	build-xcframework.sh
#	docs/development/HOWTO-add-model.md
#	docs/ops.md
#	docs/ops/SYCL.csv
#	docs/speculative.md
#	examples/sycl/update-ops-doc.sh
#	ggml/CMakeLists.txt
#	ggml/src/ggml-sycl/cpy.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	scripts/make-release-checks.sh
#	scripts/sync-ggml.last
#	tests/test-chat-auto-parser.cpp
#	tests/test-chat.cpp
#	tests/test-jinja.cpp
#	tests/test-llama-archs.cpp
#	tests/testing.h
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2026-08-20 17:08:46 +08:00
parent 1fc6e11ab8 34af94cd9a
commit f0cd0225aa
135 changed files with 3116 additions and 312 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+5 -1
View File
@@ -2303,8 +2303,12 @@ void llama_context::output_reorder() {
uint32_t llama_context::graph_max_nodes(uint32_t n_tokens) const {
uint32_t res;
if (model.arch == LLM_ARCH_QWEN3NEXT ||
if (model.arch == LLM_ARCH_KIMI_K3) {
// the n_tokens*40 budget below is exhausted at ubatch 3840
res = std::max<uint32_t>(n_tokens * 160, 64u * model.n_tensors());
} else if (model.arch == LLM_ARCH_QWEN3NEXT ||
model.arch == LLM_ARCH_KIMI_LINEAR ||
model.arch == LLM_ARCH_BAILINGMOE3 ||
model.arch == LLM_ARCH_QWEN35 ||
model.arch == LLM_ARCH_QWEN35MOE ||
model.arch == LLM_ARCH_DEEPSEEK4 ||