ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

memory : migrate from llama_kv_cache to more generic llama_memory (#14006)

Browse source 
* memory : merge llama_kv_cache into llama_memory + new `llama_memory` API

ggml-ci

* context : fix casts

ggml-ci
This commit is contained in:
Georgi Gerganov 2025-06-05 15:29:22 +03:00 • committed by GitHub
parent 3a077146a4
commit 7f37b6cf1e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 324 additions and 220 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-graph.h
View file

@ -17,7 +17,7 @@ struct ggml_tensor;
struct llama_ubatch;
struct llama_cparams;
class llama_memory_state_i;
struct llama_memory_state_i;
class llama_kv_cache_unified_state;
class llama_kv_cache_unified_iswa_state;