sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-12 20:14:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : switch to floating-point token positions

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2024-02-23 12:18:30 +02:00
parent 15499eb942
commit fc775366f1
14 changed files with 68 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@@ -1281,7 +1281,7 @@ struct llama_server_context
}
const int n_embd = llama_n_embd(model);
llama_batch batch_img = { n_eval, nullptr, (img.image_embedding + i * n_embd), nullptr, nullptr, nullptr, nullptr, slot.n_past, 1, 0, };
llama_batch batch_img = { n_eval, nullptr, (img.image_embedding + i * n_embd), nullptr, nullptr, nullptr, nullptr, (float) slot.n_past, 1, 0, };
if (llama_decode(ctx, batch_img))
{
LOG_TEE("%s : failed to eval image\n", __func__);