Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-07 13:31:13 +02:00
Code Issues Packages Projects Releases Wiki Activity

speculative : add tree-based sampling support

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2023-10-14 17:54:02 +03:00
parent 5261aee8d8
commit 4de5a2d473
11 changed files with 469 additions and 192 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/embd-input/embd-input-lib.cpp
+1 -1
View File
@@ -79,7 +79,7 @@ bool eval_float(void * model, float * input, int N){
if (n_eval > n_batch) {
n_eval = n_batch;
}
llama_batch batch = { int32_t(n_eval), nullptr, (input+i*n_emb), nullptr, nullptr, nullptr, n_past, 1, 0, };
llama_batch batch = { int32_t(n_eval), nullptr, (input+i*n_emb), nullptr, nullptr, nullptr, nullptr, n_past, 1, 0, };
if (llama_decode(ctx, batch)) {
fprintf(stderr, "%s : failed to eval\n", __func__);
return false;