llama : refactor sampling v2 (#9294)
- 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:
parent
947538acb8
commit
df270ef745
48 changed files with 3497 additions and 2914 deletions
|
@ -1,7 +1,7 @@
|
|||
#define LLAMA_API_INTERNAL
|
||||
#include "common.h"
|
||||
#include "ggml.h"
|
||||
#include "llama.h"
|
||||
#include "llama-impl.h"
|
||||
|
||||
#include <algorithm>
|
||||
#include <cassert>
|
||||
|
@ -319,8 +319,7 @@ int main(int argc, char ** argv) {
|
|||
}
|
||||
|
||||
auto cparams = llama_context_default_params();
|
||||
cparams.n_ctx = 256;
|
||||
cparams.seed = 1;
|
||||
cparams.n_ctx = 256;
|
||||
|
||||
ctx = llama_new_context_with_model(model, cparams);
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue