tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-28 19:18:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into xsn/private_batch_api

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-18 15:45:22 +01:00
parent eab5606d7b 8551c44d84
commit dc4bb64290
76 changed files with 3990 additions and 902 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/llama.h
View File

@@ -1045,6 +1045,10 @@ extern "C" {
// If set to true, the model will only attend to the past tokens
LLAMA_API void llama_set_causal_attn(struct llama_context * ctx, bool causal_attn);
// Set whether the model is in warmup mode or not
// If true, all model tensors are activated during llama_decode() to load and cache their weights.
LLAMA_API void llama_set_warmup(struct llama_context * ctx, bool warmup);
// Set abort callback
LLAMA_API void llama_set_abort_callback(struct llama_context * ctx, ggml_abort_callback abort_callback, void * abort_callback_data);