Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'd6f3030047f85a98b009189e76f441fe818ea44d' 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
parent 8b90bfe094 d6f3030047
commit a165a73120
37 changed files with 3075 additions and 376 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+9 -7
View File
@@ -2351,19 +2351,21 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_env("LLAMA_ARG_N_GPU_LAYERS"));
add_opt(common_arg(
{"-sm", "--split-mode"}, "{none,layer,row}",
{"-sm", "--split-mode"}, "{none,layer,row,tensor}",
"how to split the model across multiple GPUs, one of:\n"
"- none: use one GPU only\n"
"- layer (default): split layers and KV across GPUs\n"
"- row: split rows across GPUs",
"- layer (default): split layers and KV across GPUs (pipelined)\n"
"- row: split weight across GPUs by rows (parallelized)\n"
"- tensor: split weights and KV across GPUs (parallelized)",
[](common_params & params, const std::string & value) {
std::string arg_next = value;
if (arg_next == "none") {
if (value == "none") {
params.split_mode = LLAMA_SPLIT_MODE_NONE;
} else if (arg_next == "layer") {
} else if (value == "layer") {
params.split_mode = LLAMA_SPLIT_MODE_LAYER;
} else if (arg_next == "row") {
} else if (value == "row") {
params.split_mode = LLAMA_SPLIT_MODE_ROW;
} else if (value == "tensor") {
params.split_mode = LLAMA_SPLIT_MODE_TENSOR;
} else {
throw std::invalid_argument("invalid value");
}