tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +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

5
examples/quantize-stats/quantize-stats.cpp
View File

@ -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);