mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-09-18 16:55:14 +02:00
Merge branch 'upstream' into concedo_experimental
# Conflicts: # .github/workflows/build-cross.yml # .github/workflows/build-self-hosted.yml # .github/workflows/release.yml # examples/llama.android/lib/src/main/cpp/CMakeLists.txt # ggml/CMakeLists.txt # ggml/src/ggml-rpc/CMakeLists.txt # ggml/src/ggml-rpc/ggml-rpc.cpp # ggml/src/ggml-sycl/mmvq.cpp # ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp # ggml/src/ggml-webgpu/ggml-webgpu.cpp # scripts/sync_vendor.py # tests/test-chat.cpp # tests/test-mtmd-c-api.c # tools/server/README.md
This commit is contained in:
+5
-5
@@ -294,7 +294,7 @@ static bool common_params_handle_remote_preset(common_params & params, llama_exa
|
||||
hf_tag = "default";
|
||||
}
|
||||
|
||||
std::string model_endpoint = get_model_endpoint();
|
||||
std::string model_endpoint = common_get_model_endpoint();
|
||||
auto preset_url = model_endpoint + hf_repo + "/resolve/main/preset.ini";
|
||||
|
||||
// prepare local path for caching
|
||||
@@ -1318,13 +1318,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
||||
}
|
||||
).set_env("LLAMA_ARG_KV_UNIFIED").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_PERPLEXITY, LLAMA_EXAMPLE_BATCHED, LLAMA_EXAMPLE_BENCH, LLAMA_EXAMPLE_PARALLEL}));
|
||||
add_opt(common_arg(
|
||||
{"--clear-idle"},
|
||||
{"--no-clear-idle"},
|
||||
{"--cache-idle-slots"},
|
||||
{"--no-cache-idle-slots"},
|
||||
"save and clear idle slots on new task (default: enabled, requires unified KV and cache-ram)",
|
||||
[](common_params & params, bool value) {
|
||||
params.clear_idle = value;
|
||||
params.cache_idle_slots = value;
|
||||
}
|
||||
).set_env("LLAMA_ARG_CLEAR_IDLE").set_examples({LLAMA_EXAMPLE_SERVER}));
|
||||
).set_env("LLAMA_ARG_CACHE_IDLE_SLOTS").set_examples({LLAMA_EXAMPLE_SERVER}));
|
||||
add_opt(common_arg(
|
||||
{"--context-shift"},
|
||||
{"--no-context-shift"},
|
||||
|
||||
Reference in New Issue
Block a user