Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-03 19:42:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-linux-cross.yml
#	.github/workflows/build.yml
#	CODEOWNERS
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cuda/fattn.cu
#	ggml/src/ggml-webgpu/CMakeLists.txt
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat.tmpl.wgsl
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tools/llama-bench/llama-bench.cpp
#	tools/rpc/README.md
#	tools/server/README.md
This commit is contained in:
Concedo
2025-10-09 01:33:27 +08:00
parent 224800b33b d2ee056e1d
commit b6f6338bba
32 changed files with 1556 additions and 636 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+7 -3
View File
@@ -2607,6 +2607,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.no_extra_bufts = true;
}
).set_env("LLAMA_ARG_NO_REPACK"));
add_opt(common_arg(
{"--no-host"},
"bypass host buffer allowing extra buffers to be used",
[](common_params & params) {
params.no_host = true;
}
).set_env("LLAMA_ARG_NO_HOST"));
add_opt(common_arg(
{"-ctk", "--cache-type-k"}, "TYPE",
string_format(
@@ -3875,7 +3882,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.model.hf_repo = "ggml-org/bge-small-en-v1.5-Q8_0-GGUF";
params.model.hf_file = "bge-small-en-v1.5-q8_0.gguf";
params.pooling_type = LLAMA_POOLING_TYPE_NONE;
params.embd_normalize = 2;
params.n_ctx = 512;
params.verbose_prompt = true;
@@ -3889,7 +3895,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.model.hf_repo = "ggml-org/e5-small-v2-Q8_0-GGUF";
params.model.hf_file = "e5-small-v2-q8_0.gguf";
params.pooling_type = LLAMA_POOLING_TYPE_NONE;
params.embd_normalize = 2;
params.n_ctx = 512;
params.verbose_prompt = true;
@@ -3903,7 +3908,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.model.hf_repo = "ggml-org/gte-small-Q8_0-GGUF";
params.model.hf_file = "gte-small-q8_0.gguf";
params.pooling_type = LLAMA_POOLING_TYPE_NONE;
params.embd_normalize = 2;
params.n_ctx = 512;
params.verbose_prompt = true;