Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 16:55:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '67e3f6f60155870d4b5ce727515aa81e5a7b4753' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	.github/workflows/server.yml
#	ci/run.sh
#	docs/backend/CANN.md
#	docs/backend/OPENCL.md
#	examples/batched/batched.cpp
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cuda/CMakeLists.txt
#	src/llama-context.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo
2026-01-05 20:52:20 +08:00
parent c9308570b2 67e3f6f601
commit 4889f3a11d
38 changed files with 4047 additions and 284 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+19
View File
@@ -1094,6 +1094,7 @@ struct common_init_result::impl {
std::vector<llama_adapter_lora_ptr> lora;
std::vector<common_sampler_ptr> samplers;
std::vector<llama_sampler_seq_config> samplers_seq_config;
};
common_init_result::common_init_result(common_params & params) :
@@ -1170,10 +1171,19 @@ common_init_result::common_init_result(common_params & params) :
// params.sampling.dry_penalty_last_n = llama_n_ctx(lctx);
//}
// init the backend samplers as part of the context creation
pimpl->samplers.resize(cparams.n_seq_max);
pimpl->samplers_seq_config.resize(cparams.n_seq_max);
for (int i = 0; i < (int) cparams.n_seq_max; ++i) {
pimpl->samplers[i].reset(common_sampler_init(model, params.sampling));
pimpl->samplers_seq_config[i] = { i, common_sampler_get(pimpl->samplers[i].get()) };
}
// TODO: temporarily gated behind a flag
if (params.sampling.backend_sampling) {
cparams.samplers = pimpl->samplers_seq_config.data();
cparams.n_samplers = pimpl->samplers_seq_config.size();
}
llama_context * lctx = llama_init_from_model(model, cparams);
@@ -1197,6 +1207,12 @@ common_sampler * common_init_result::sampler(llama_seq_id seq_id) {
return pimpl->samplers[seq_id].get();
}
void common_init_result::reset_samplers() {
for (int i = 0; i < (int) pimpl->samplers.size(); ++i) {
llama_sampler_reset(common_sampler_get(pimpl->samplers[i].get()));
}
}
std::vector<llama_adapter_lora_ptr> & common_init_result::lora() {
return pimpl->lora;
}
@@ -1312,6 +1328,9 @@ common_init_result_ptr common_init_from_params(common_params & params) {
llama_synchronize(lctx);
llama_perf_context_reset(lctx);
llama_set_warmup(lctx, false);
// reset samplers to reset RNG state after warmup to the seeded state
res->reset_samplers();
}
return res;