vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)

Browse source 
* refactor llama_batch_get_one

* adapt all examples

* fix simple.cpp

* fix llama_bench

* fix

* fix context shifting

* free batch before return

* use common_batch_add, reuse llama_batch in loop

* null terminated seq_id list

* fix save-load-state example

* fix perplexity

* correct token pos in llama_batch_allocr
This commit is contained in:
Xuan Son Nguyen 2024-10-18 23:18:01 +02:00 • committed by GitHub
parent afd9909a64
commit cda0e4b648
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
22 changed files with 205 additions and 118 deletions
Download patch file Download diff file Expand all files Collapse all files

6
examples/speculative/speculative.cpp
View file

@ -155,9 +155,9 @@ int main(int argc, char ** argv) {
const auto t_enc_start = ggml_time_us();
// eval the prompt with both models
llama_decode(ctx_tgt, llama_batch_get_one( inp.data(), n_input - 1, 0, 0));
llama_decode(ctx_tgt, llama_batch_get_one(&inp.back(), 1, n_input - 1, 0));
llama_decode(ctx_dft, llama_batch_get_one( inp.data(), n_input, 0, 0));
llama_decode(ctx_tgt, llama_batch_get_one( inp.data(), n_input - 1));
llama_decode(ctx_tgt, llama_batch_get_one(&inp.back(), 1));
llama_decode(ctx_dft, llama_batch_get_one( inp.data(), n_input));
const auto t_enc_end = ggml_time_us();