Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 01:31:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.clang-tidy
#	.devops/musa.Dockerfile
#	.github/workflows/build-linux-cross.yml
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	.gitignore
#	CODEOWNERS
#	CONTRIBUTING.md
#	README.md
#	build-xcframework.sh
#	ci/README-MUSA.md
#	ci/run.sh
#	common/CMakeLists.txt
#	docs/docker.md
#	examples/CMakeLists.txt
#	examples/eval-callback/CMakeLists.txt
#	examples/model-conversion/Makefile
#	examples/model-conversion/README.md
#	examples/model-conversion/logits.cpp
#	examples/model-conversion/scripts/causal/compare-logits.py
#	examples/model-conversion/scripts/causal/run-org-model.py
#	examples/model-conversion/scripts/embedding/compare-embeddings-logits.sh
#	examples/model-conversion/scripts/embedding/run-converted-model.sh
#	examples/model-conversion/scripts/embedding/run-original-model.py
#	examples/model-conversion/scripts/utils/check-nmse.py
#	examples/model-conversion/scripts/utils/inspect-org-model.py
#	examples/model-conversion/scripts/utils/semantic_check.py
#	ggml/CMakeLists.txt
#	ggml/include/ggml-zdnn.h
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/set_rows.cl
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/set_rows.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-quantize-perf.cpp
#	tests/test-tokenizers-repo.sh
#	tools/perplexity/perplexity.cpp
#	tools/server/tests/README.md
This commit is contained in:
Concedo
2025-09-27 17:09:14 +08:00
parent cbb8a3feb5 72b24d96c6
commit b120e107f9
112 changed files with 10916 additions and 4106 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-memory-recurrent.cpp
+8
View File
@@ -359,6 +359,14 @@ llama_pos llama_memory_recurrent::seq_pos_max(llama_seq_id seq_id) const {
return result;
}
std::map<ggml_backend_buffer_type_t, size_t> llama_memory_recurrent::memory_breakdown() const {
std::map<ggml_backend_buffer_type_t, size_t> ret;
for (const ggml_backend_buffer_ptr & buf_ptr : bufs) {
ret[ggml_backend_buffer_get_type(buf_ptr.get())] += ggml_backend_buffer_get_size(buf_ptr.get());
}
return ret;
}
llama_memory_context_ptr llama_memory_recurrent::init_batch(llama_batch_allocr & balloc, uint32_t n_ubatch, bool embd_all) {
do {
balloc.split_reset();