public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-05 22:11:21 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2025-10-12 11:16:23 +03:00
parent ed6a3063ec
commit ff4c1a5a53
19 changed files with 565 additions and 104 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/llama-kv-cache.cpp
+2 -5
View File
@@ -123,11 +123,8 @@ llama_kv_cache::llama_kv_cache(
throw std::runtime_error("failed to create ggml context for kv cache");
}
ggml_tensor * k;
ggml_tensor * v;
k = ggml_new_tensor_3d(ctx, type_k, n_embd_k_gqa, kv_size, n_stream);
v = ggml_new_tensor_3d(ctx, type_v, n_embd_v_gqa, kv_size, n_stream);
ggml_tensor * k = ggml_new_tensor_3d(ctx, type_k, n_embd_k_gqa, kv_size, n_stream);
ggml_tensor * v = ggml_new_tensor_3d(ctx, type_v, n_embd_v_gqa, kv_size, n_stream);
ggml_format_name(k, "cache_k_l%d", il);
ggml_format_name(v, "cache_v_l%d", il);