starred/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-18 14:54:11 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update vendor ggml code to a5bb8ba4 (#13832)

Browse Source 
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Shalini Salomi Bodapati <Shalini.Salomi.Bodapati@ibm.com>
This commit is contained in:
Jeffrey Morgan
2026-02-02 17:31:59 -08:00
committed by GitHub
parent 8f4a008139
commit ef00199fb4
241 changed files with 21271 additions and 5074 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
llama/llama.cpp/common/common.cpp vendored
View File

@@ -251,7 +251,7 @@ bool set_process_priority(enum ggml_sched_priority prio) {
case GGML_SCHED_PRIO_REALTIME: p = -20; break;
}
if (!setpriority(PRIO_PROCESS, 0, p)) {
if (setpriority(PRIO_PROCESS, 0, p) != 0) {
LOG_WRN("failed to set process priority %d : %s (%d)\n", prio, strerror(errno), errno);
return false;
}
@@ -1078,12 +1078,15 @@ struct common_init_result::impl {
impl() = default;
~impl() = default;
// note: the order in which model, context, etc. are declared matters because their destructors will be called bottom-to-top
llama_model_ptr model;
llama_context_ptr context;
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) :
@@ -1092,9 +1095,9 @@ 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, to report bugs during this step use -fit off (or --verbose if you can't)\n", __func__);
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__);
llama_params_fit(params.model.path.c_str(), &mparams, &cparams,
params.tensor_split, params.tensor_buft_overrides.data(), params.fit_params_target, params.fit_params_min_ctx,
params.tensor_split, 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);
}
@@ -1107,6 +1110,25 @@ common_init_result::common_init_result(common_params & params) :
const llama_vocab * vocab = llama_model_get_vocab(model);
// load and optionally apply lora adapters (must be loaded before context creation)
for (auto & la : params.lora_adapters) {
llama_adapter_lora_ptr lora;
lora.reset(llama_adapter_lora_init(model, la.path.c_str()));
if (lora == nullptr) {
LOG_ERR("%s: failed to load lora adapter '%s'\n", __func__, la.path.c_str());
pimpl->model.reset(model);
return;
}
char buf[1024];
la.ptr = lora.get();
llama_adapter_meta_val_str(la.ptr, "adapter.lora.task_name", buf, sizeof(buf));
la.task_name = buf;
llama_adapter_meta_val_str(la.ptr, "adapter.lora.prompt_prefix", buf, sizeof(buf));
la.prompt_prefix = buf;
pimpl->lora.emplace_back(std::move(lora)); // copy to list of loaded adapters
}
// updates params.sampling
// TODO: fix naming
common_init_sampler_from_model(model, params.sampling);
@@ -1141,10 +1163,18 @@ 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()) };
}
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);
@@ -1168,6 +1198,12 @@ 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;
}
@@ -1243,24 +1279,6 @@ common_init_result_ptr common_init_from_params(common_params & params) {
}
}
// load and optionally apply lora adapters
for (auto & la : params.lora_adapters) {
llama_adapter_lora_ptr lora;
lora.reset(llama_adapter_lora_init(model, la.path.c_str()));
if (lora == nullptr) {
LOG_ERR("%s: failed to apply lora adapter '%s'\n", __func__, la.path.c_str());
return res;
}
char buf[1024];
la.ptr = lora.get();
llama_adapter_meta_val_str(la.ptr, "adapter.lora.task_name", buf, sizeof(buf));
la.task_name = buf;
llama_adapter_meta_val_str(la.ptr, "adapter.lora.prompt_prefix", buf, sizeof(buf));
la.prompt_prefix = buf;
res->lora().emplace_back(std::move(lora)); // copy to list of loaded adapters
}
if (!params.lora_init_without_apply) {
common_set_adapter_lora(lctx, params.lora_adapters);
}
@@ -1301,6 +1319,9 @@ 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;
@@ -1339,14 +1360,12 @@ struct llama_model_params common_model_params_to_llama(common_params & params) {
mparams.devices = params.devices.data();
}
if (params.n_gpu_layers != -1) {
mparams.n_gpu_layers = params.n_gpu_layers;
}
mparams.n_gpu_layers = params.n_gpu_layers;
mparams.main_gpu = params.main_gpu;
mparams.split_mode = params.split_mode;
mparams.tensor_split = params.tensor_split;
mparams.use_mmap = params.use_mmap;
mparams.use_direct_io = params.use_direct_io;
mparams.use_mlock = params.use_mlock;
mparams.check_tensors = params.check_tensors;
mparams.use_extra_bufts = !params.no_extra_bufts;