vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-18 23:49:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/intel.Dockerfile
#	.github/workflows/build-cross.yml
#	.github/workflows/build-sycl.yml
#	.github/workflows/build.yml
#	.github/workflows/editorconfig.yml
#	.github/workflows/release.yml
#	cmake/riscv64-spacemit-linux-gnu-gcc.cmake
#	docs/backend/OPENVINO.md
#	docs/backend/SYCL.md
#	docs/build-riscv64-spacemit.md
#	docs/ops.md
#	docs/ops/WebGPU.csv
#	embd_res/ggml-vocab-qwen35.gguf
#	embd_res/ggml-vocab-qwen35.gguf.inp
#	embd_res/ggml-vocab-qwen35.gguf.out
#	examples/model-conversion/Makefile
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/hmx-flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-utils.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-utils.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-sycl/common.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/common_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_tile.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_reduce.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_split.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/get_rows.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec_acc.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/unary.wgsl
#	ggml/src/ggml-zendnn/CMakeLists.txt
#	ggml/src/ggml-zendnn/ggml-zendnn.cpp
#	scripts/snapdragon/adb/run-completion.sh
#	tests/CMakeLists.txt
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/mtmd/clip-impl.h
#	tools/mtmd/clip.cpp
#	tools/mtmd/clip.h
#	tools/server/README.md
This commit is contained in:
Concedo 2026-05-14 19:04:04 +08:00
commit cc82c3164e
62 changed files with 18693 additions and 7034 deletions
Download patch file Download diff file Expand all files Collapse all files

29
common/common.cpp
View file

@ -372,15 +372,29 @@ void common_init() {
SetConsoleCP(CP_UTF8);
#endif
llama_log_set(common_log_default_callback, NULL);
common_log_set_prefix(common_log_main(), true);
common_log_set_timestamps(common_log_main(), true);
llama_log_set(common_log_default_callback, NULL);
}
void common_params_print_info(const common_params & params) {
#ifdef NDEBUG
const char * build_type = "";
#else
const char * build_type = " (debug)";
#endif
LOG_TRC("%s: build %d (%s) with %s for %s%s\n", __func__, llama_build_number(), llama_commit(), llama_compiler(), llama_build_target(), build_type);
LOG_DBG("build: %d (%s) with %s for %s%s\n", llama_build_number(), llama_commit(), llama_compiler(), llama_build_target(), build_type);
LOG_INF("log_info: verbosity = %d (adjust with the `-lv N` CLI arg)\n", common_log_get_verbosity_thold());
LOG_INF("device_info:\n");
for (size_t i = 0; i < ggml_backend_dev_count(); ++i) {
auto * dev = ggml_backend_dev_get(i);
size_t free, total;
ggml_backend_dev_memory(dev, &free, &total);
LOG_INF(" - %-8s: %s (%zu MiB, %zu MiB free)\n", ggml_backend_dev_name(dev), ggml_backend_dev_description(dev), total / 1024 / 1024, free / 1024 / 1024);
}
LOG_INF("%s\n", common_params_get_system_info(params).c_str());
}
std::string common_params_get_system_info(const common_params & params) {
@ -1153,7 +1167,8 @@ common_init_result::common_init_result(common_params & params) :
auto cparams = common_context_params_to_llama(params);
if (params.fit_params) {
LOG_INF("%s: fitting params to device memory, for bugs during this step try to reproduce them with -fit off, or provide --verbose logs if the bug only occurs with -fit on\n", __func__);
LOG_INF("%s: fitting params to device memory ...\n", __func__);
LOG_INF("%s: (for bugs during this step try to reproduce them with -fit off, or provide --verbose logs if the bug only occurs with -fit on)\n", __func__);
common_fit_params(params.model.path.c_str(), &mparams, &cparams,
params.tensor_split,
params.tensor_buft_overrides.data(),
@ -1202,7 +1217,7 @@ common_init_result::common_init_result(common_params & params) :
// initialize once
for (llama_token i = 0; i < llama_vocab_n_tokens(vocab); i++) {
if (llama_vocab_is_eog(vocab, i)) {
LOG_INF("%s: added %s logit bias = %f\n", __func__, common_token_to_piece(vocab, i).c_str(), -INFINITY);
LOG_TRC("%s: added %s logit bias = %f\n", __func__, common_token_to_piece(vocab, i).c_str(), -INFINITY);
params.sampling.logit_bias_eog.push_back({i, -INFINITY});
}
}
@ -1215,12 +1230,12 @@ common_init_result::common_init_result(common_params & params) :
}
//if (params.sampling.penalty_last_n == -1) {
// LOG_INF("%s: setting penalty_last_n to ctx_size = %d\n", __func__, llama_n_ctx(lctx));
// LOG_TRC("%s: setting penalty_last_n to ctx_size = %d\n", __func__, llama_n_ctx(lctx));
// params.sampling.penalty_last_n = llama_n_ctx(lctx);
//}
//if (params.sampling.dry_penalty_last_n == -1) {
// LOG_INF("%s: setting dry_penalty_last_n to ctx_size = %d\n", __func__, llama_n_ctx(lctx));
// LOG_TRC("%s: setting dry_penalty_last_n to ctx_size = %d\n", __func__, llama_n_ctx(lctx));
// params.sampling.dry_penalty_last_n = llama_n_ctx(lctx);
//}
@ -1428,7 +1443,7 @@ common_context_seq_rm_type common_context_can_seq_rm(llama_context * ctx) {
// try to remove the last tokens
if (!llama_memory_seq_rm(mem, 0, 1, -1)) {
LOG_WRN("%s: the context does not support partial sequence removal\n", __func__);
LOG_TRC("%s: the context does not support partial sequence removal\n", __func__);
res = COMMON_CONTEXT_SEQ_RM_TYPE_FULL;
goto done;
}