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

2
examples/llava/minicpmv-cli.cpp
View file

@ -97,7 +97,7 @@ static bool eval_tokens(struct llama_context * ctx_llama, std::vector<llama_toke
if (n_eval > n_batch) {
n_eval = n_batch;
}
if (llama_decode(ctx_llama, llama_batch_get_one(&tokens[i], n_eval, *n_past, 0))) {
if (llama_decode(ctx_llama, llama_batch_get_one(&tokens[i], n_eval))) {
LOG_ERR("%s : failed to eval. token %d/%d (batch size %d, n_past %d)\n", __func__, i, N, n_batch, *n_past);
return false;
}