Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-09 06:19:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/cann.Dockerfile
#	.devops/cpu.Dockerfile
#	.devops/cuda.Dockerfile
#	.devops/intel.Dockerfile
#	.devops/llama-cli-cann.Dockerfile
#	.devops/musa.Dockerfile
#	.devops/openvino.Dockerfile
#	.devops/rocm.Dockerfile
#	.devops/s390x.Dockerfile
#	.devops/vulkan.Dockerfile
#	.github/ISSUE_TEMPLATE/011-bug-results.yml
#	.github/ISSUE_TEMPLATE/019-bug-misc.yml
#	.github/workflows/build-and-test-snapdragon.yml
#	.github/workflows/docker.yml
#	.github/workflows/server-self-hosted.yml
#	.github/workflows/ui-ci.yml
#	.pi/gg/SYSTEM.md
#	README.md
#	common/arg.cpp
#	docs/backend/SYCL.md
#	docs/backend/snapdragon/CMakeUserPresets.json
#	docs/backend/snapdragon/README.md
#	docs/speculative.md
#	examples/save-load-state/save-load-state.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/rope-ops.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/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/gated_delta_net.wgsl
#	tools/cli/README.md
#	tools/server/README.md
This commit is contained in:
Concedo
2026-05-20 18:48:34 +08:00
parent 643862ac7d 585080d310
commit 7d987af23a
77 changed files with 1291 additions and 1048 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+13 -28
View File
@@ -1166,7 +1166,7 @@ struct common_init_result::impl {
std::vector<llama_sampler_seq_config> samplers_seq_config;
};
common_init_result::common_init_result(common_params & params) :
common_init_result::common_init_result(common_params & params, bool model_only) :
pimpl(new impl{}) {
auto mparams = common_model_params_to_llama(params);
auto cparams = common_context_params_to_llama(params);
@@ -1179,7 +1179,7 @@ common_init_result::common_init_result(common_params & params) :
params.tensor_buft_overrides.data(),
params.fit_params_target.data(),
params.fit_params_min_ctx,
params.verbosity >= 4 ? GGML_LOG_LEVEL_DEBUG : GGML_LOG_LEVEL_ERROR);
params.verbosity >= LOG_LEVEL_DEBUG ? GGML_LOG_LEVEL_DEBUG : GGML_LOG_LEVEL_ERROR);
}
llama_model * model = llama_model_load_from_file(params.model.path.c_str(), mparams);
@@ -1189,6 +1189,10 @@ common_init_result::common_init_result(common_params & params) :
pimpl->model.reset(model);
if (model_only) {
return;
}
const llama_vocab * vocab = llama_model_get_vocab(model);
// load and optionally apply lora adapters
@@ -1258,29 +1262,6 @@ common_init_result::common_init_result(common_params & params) :
cparams.n_samplers = pimpl->samplers_seq_config.size();
}
// [TAG_RS_STATE_ROLLBACK_SUPPORT]
// TODO: ngram speculative methods require checkpointing in addition to partial RS rollback
// currently this is not supported. so we disable the partial rollback
if (cparams.n_rs_seq > 0 && (llama_model_is_recurrent(model) || llama_model_is_hybrid(model))) {
auto & types = params.speculative.types;
for (int i = 0; i < (int) types.size(); i++) {
if (types[i] == COMMON_SPECULATIVE_TYPE_NONE) {
continue;
}
if (types[i] == COMMON_SPECULATIVE_TYPE_DRAFT_MTP) {
continue;
}
cparams.n_rs_seq = 0;
LOG_WRN("%s: recurrent state rollback is not compatible with '%s' - disabling rollback support\n", __func__,
common_speculative_type_to_str(types[i]).c_str());
break;
}
}
llama_context * lctx = llama_init_from_model(model, cparams);
if (lctx == NULL) {
LOG_ERR("%s: failed to create context with model '%s'\n", __func__, params.model.path.c_str());
@@ -1315,8 +1296,8 @@ std::vector<llama_adapter_lora_ptr> & common_init_result::lora() {
return pimpl->lora;
}
common_init_result_ptr common_init_from_params(common_params & params) {
common_init_result_ptr res(new common_init_result(params));
common_init_result_ptr common_init_from_params(common_params & params, bool model_only) {
common_init_result_ptr res(new common_init_result(params, model_only));
llama_model * model = res->model();
if (model == NULL) {
@@ -1324,6 +1305,10 @@ common_init_result_ptr common_init_from_params(common_params & params) {
return res;
}
if (model_only) {
return res;
}
llama_context * lctx = res->context();
if (lctx == NULL) {
LOG_ERR("%s: failed to create context with model '%s'\n", __func__, params.model.path.c_str());
@@ -1387,7 +1372,7 @@ common_init_result_ptr common_init_from_params(common_params & params) {
}
if (params.warmup) {
LOG_WRN("%s: warming up the model with an empty run - please wait ... (--no-warmup to disable)\n", __func__);
LOG_INF("%s: warming up the model with an empty run - please wait ... (--no-warmup to disable)\n", __func__);
llama_set_warmup(lctx, true);