CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

kv-cache : drop the "unified" prefix (#15467)

Browse Source 
* kv-cache : drop the "unified" prefix

ggml-ci

* cont : fix comment [no ci]
This commit is contained in:
Georgi Gerganov
2025-08-21 17:00:33 +03:00
committed by GitHub
parent ad294df03f
commit 715a6db02c
15 changed files with 346 additions and 360 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/llama-memory.h
View File

@@ -36,8 +36,8 @@ bool llama_memory_status_is_fail(llama_memory_status status);
// the interface for managing the memory context during batch processing
// this interface is implemented per memory type. see:
// - llama_kv_cache_unified_context
// - llama_kv_cache_unified_iswa_context
// - llama_kv_cache_context
// - llama_kv_cache_iswa_context
// ...
//
// the only method that should mutate the memory and the memory context is llama_memory_i::apply()
@@ -109,8 +109,3 @@ struct llama_memory_i {
};
using llama_memory_ptr = std::unique_ptr<llama_memory_i>;
// TODO: temporary until the llama_kv_cache is removed from the public API
struct llama_kv_cache : public llama_memory_i {
virtual ~llama_kv_cache() = default;
};