tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 12:35:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : cont

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-01-13 14:56:52 +02:00
parent f78b396ee7
commit e4550fbafc
19 changed files with 128 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/imatrix/imatrix.cpp
View File

@ -431,6 +431,8 @@ static bool compute_imatrix(llama_context * ctx, const common_params & params) {
const llama_model * model = llama_get_model(ctx);
const llama_vocab * vocab = llama_model_get_vocab(model);
llama_kv_cache * kv = llama_get_kv_cache(ctx);
const bool add_bos = llama_vocab_get_add_bos(vocab);
const int n_ctx = llama_n_ctx(ctx);
@ -497,7 +499,7 @@ static bool compute_imatrix(llama_context * ctx, const common_params & params) {
const auto t_start = std::chrono::high_resolution_clock::now();
// clear the KV cache
llama_kv_cache_clear(ctx);
llama_kv_cache_clear(kv);
llama_batch batch = llama_batch_init(n_batch, 0, 1);