tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : refactor sampling v2 (#9294)

Browse Source 
- Add `struct llama_sampler` and `struct llama_sampler_i`
- Add `llama_sampler_` API
- Add `llama_sampler_chain_` API for chaining multiple samplers
- Remove `LLAMA_API_INTERNAL`
- Add `llama_perf_` API and remove old `llama_print_timings` and `llama_reset_timings`
This commit is contained in:
Georgi Gerganov
2024-09-07 15:16:19 +03:00
committed by GitHub
parent 947538acb8
commit df270ef745
48 changed files with 3497 additions and 2914 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/embedding/embedding.cpp
View File

@ -90,13 +90,7 @@ int main(int argc, char ** argv) {
print_build_info();
if (params.seed == LLAMA_DEFAULT_SEED) {
params.seed = time(NULL);
}
fprintf(stderr, "%s: seed = %u\n", __func__, params.seed);
std::mt19937 rng(params.seed);
LOG_TEE("%s: seed = %u\n", __func__, params.sparams.seed);
llama_backend_init();
llama_numa_init(params.numa);
@ -313,8 +307,10 @@ int main(int argc, char ** argv) {
if (notArray) fprintf(stdout, "\n}\n");
}
LOG_TEE("\n");
llama_perf_print(ctx, LLAMA_PERF_TYPE_CONTEXT);
// clean up
llama_print_timings(ctx);
llama_batch_free(batch);
llama_free(ctx);
llama_free_model(model);