tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-17 21:51:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

apply to the rest

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-13 22:36:27 +01:00
parent 4aabf4e8f4
commit 47086fa82d
18 changed files with 242 additions and 323 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
include/llama.h
View File

@@ -995,9 +995,9 @@ extern "C" {
// Stores the encoder output internally for later use by the decoder cross-attention layers.
// 0 - success
// < 0 - error. the KV cache state is restored to the state before this call
DEPRECATED(LLAMA_API int32_t llama_encode(
LLAMA_API int32_t llama_encode(
struct llama_context * ctx,
struct llama_batch batch), "use llama_batch_ext API instead");
struct llama_batch batch);
LLAMA_API int32_t llama_encode_ext(
struct llama_context * ctx,
@@ -1007,9 +1007,9 @@ extern "C" {
// 0 - success
// 1 - could not find a KV slot for the batch (try reducing the size of the batch or increase the context)
// < 0 - error. the KV cache state is restored to the state before this call
DEPRECATED(LLAMA_API int32_t llama_decode(
LLAMA_API int32_t llama_decode(
struct llama_context * ctx,
struct llama_batch batch), "use llama_batch_ext API instead");
struct llama_batch batch);
LLAMA_API int32_t llama_decode_ext(
struct llama_context * ctx,