vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-04-28 03:30:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge commit 'd6f3030047' into concedo_experimental

Browse source 
# Conflicts:
#	examples/model-conversion/scripts/causal/run-casual-gen-embeddings-org.py
#	examples/model-conversion/scripts/utils/semantic_check.py
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/amx/amx.cpp
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-openvino/ggml-openvino.cpp
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-virtgpu/ggml-backend-buffer.cpp
#	ggml/src/ggml-virtgpu/ggml-backend.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	ggml/src/ggml-zendnn/ggml-zendnn.cpp
#	pyproject.toml
#	requirements/requirements-convert_legacy_llama.txt
#	requirements/requirements-tool_bench.txt
#	src/llama-model.cpp
#	src/llama.cpp
#	tests/test-llama-archs.cpp
#	tests/test-tokenizer-0.py
#	tests/test-tokenizer-random.py
#	tools/llama-bench/llama-bench.cpp
#	tools/perplexity/perplexity.cpp
This commit is contained in:
Concedo 2026-04-11 11:10:55 +08:00
commit a165a73120
37 changed files with 3075 additions and 376 deletions
Download patch file Download diff file Expand all files Collapse all files

7
include/llama.h
View file

@ -195,9 +195,10 @@ extern "C" {
LLAMA_API const char * llama_flash_attn_type_name(enum llama_flash_attn_type flash_attn_type);
enum llama_split_mode {
LLAMA_SPLIT_MODE_NONE = 0, // single GPU
LLAMA_SPLIT_MODE_LAYER = 1, // split layers and KV across GPUs
LLAMA_SPLIT_MODE_ROW = 2, // split layers and KV across GPUs, use tensor parallelism if supported
LLAMA_SPLIT_MODE_NONE = 0, // single GPU
LLAMA_SPLIT_MODE_LAYER = 1, // split layers and KV across GPUs
LLAMA_SPLIT_MODE_ROW = 2, // split layers and KV across GPUs, use tensor parallelism if supported
LLAMA_SPLIT_MODE_TENSOR = 3,
};
// TODO: simplify (https://github.com/ggml-org/llama.cpp/pull/9294#pullrequestreview-2286561979)