tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 04:15:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : deprecate llama_kv_self_ API (#14030)

Browse Source 
* llama : deprecate llama_kv_self_ API

ggml-ci

* llama : allow llama_memory_(nullptr)

ggml-ci

* memory : add flag for optional data clear in llama_memory_clear

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-06 14:11:15 +03:00
committed by GitHub
parent 487a5e0401
commit 745aa5319b
34 changed files with 206 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/embedding/embedding.cpp
View File

@ -37,7 +37,7 @@ static void batch_decode(llama_context * ctx, llama_batch & batch, float * outpu
const enum llama_pooling_type pooling_type = llama_pooling_type(ctx);
// clear previous kv_cache values (irrelevant for embeddings)
llama_kv_self_clear(ctx);
llama_memory_clear(llama_get_memory(ctx), true);
// run model
LOG_INF("%s: n_tokens = %d, n_seq = %d\n", __func__, batch.n_tokens, n_seq);