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:
Concedo
2026-04-20 20:19:11 +08:00
86 changed files with 1384 additions and 1240 deletions
+5 -5
View File
@@ -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"},