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 branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	README.md
#	ci/run.sh
#	docs/backend/CANN.md
#	examples/speculative/speculative.cpp
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/flash_attn_f16.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_f16.cl
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/gguf.cpp
#	src/llama-context.cpp
#	tests/test-sampling.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2025-09-03 17:16:42 +08:00
parent 5c4ad392ea 5eae934883
commit 2562129271
35 changed files with 1715 additions and 599 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+10 -10
View File
@@ -1550,11 +1550,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
{"-fa", "--flash-attn"}, "FA",
string_format("set Flash Attention use ('on', 'off', or 'auto', default: '%s')", llama_flash_attn_type_name(params.flash_attn_type)),
[](common_params & params, const std::string & value) {
if (value == "on" || value == "enabled") {
if (value == "on" || value == "enabled" || value == "1") {
params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_ENABLED;
} else if (value == "off" || value == "disabled") {
} else if (value == "off" || value == "disabled" || value == "0") {
params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_DISABLED;
} else if (value == "auto") {
} else if (value == "auto" || value == "-1") {
params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_AUTO;
} else {
throw std::runtime_error(string_format("error: unkown value for --flash-attn: '%s'\n", value.c_str()));
@@ -2964,13 +2964,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.endpoint_metrics = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_METRICS"));
add_opt(common_arg(
{"--slots"},
string_format("enable slots monitoring endpoint (default: %s)", params.endpoint_slots ? "enabled" : "disabled"),
[](common_params & params) {
params.endpoint_slots = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_SLOTS"));
add_opt(common_arg(
{"--props"},
string_format("enable changing global properties via POST /props (default: %s)", params.endpoint_props ? "enabled" : "disabled"),
@@ -2978,6 +2971,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.endpoint_props = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_PROPS"));
add_opt(common_arg(
{"--slots"},
string_format("enable slots monitoring endpoint (default: %s)", params.endpoint_slots ? "enabled" : "disabled"),
[](common_params & params) {
params.endpoint_slots = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_SLOTS"));
add_opt(common_arg(
{"--no-slots"},
"disables slots monitoring endpoint",