highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-08-04 00:53:12 +02:00
Code Issues Packages Projects Releases Wiki Activity

chore: update mllama to use ollama engine (#10637)

Browse Source
This commit is contained in:
Michael Yang
2025-05-13 17:36:02 -07:00
committed by GitHub
parent 0478d440f0
commit 23125648b8
67 changed files with 785 additions and 4354 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
llama/llama.cpp/src/llama-batch.cpp vendored
View File

@@ -320,7 +320,6 @@ struct llama_batch llama_batch_get_one(
/*n_tokens =*/ n_tokens,
/*tokens =*/ tokens,
/*embd =*/ nullptr,
/*n_embd =*/ 0,
/*pos =*/ nullptr,
/*n_seq_id =*/ nullptr,
/*seq_id =*/ nullptr,
@@ -333,7 +332,6 @@ struct llama_batch llama_batch_init(int32_t n_tokens_alloc, int32_t embd, int32_
/*n_tokens =*/ 0,
/*tokens =*/ nullptr,
/*embd =*/ nullptr,
/*n_embd =*/ 0,
/*pos =*/ nullptr,
/*n_seq_id =*/ nullptr,
/*seq_id =*/ nullptr,
@@ -342,7 +340,6 @@ struct llama_batch llama_batch_init(int32_t n_tokens_alloc, int32_t embd, int32_
if (embd) {
batch.embd = (float *) malloc(sizeof(float) * n_tokens_alloc * embd);
batch.n_embd = embd;
} else {
batch.token = (llama_token *) malloc(sizeof(llama_token) * n_tokens_alloc);
}