ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-06 06:20:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Bump GGML_MAX_CONTEXTS to allow loading more shards (#611)

Browse Source 
* Bump GGML_MAX_CONTEXTS to allow loading more shards

This var prevents more than 64 shards from being loaded - Specifically relevant for large models such as DeepSeek R1.

* https://github.com/ikawrakow/ik_llama.cpp/pull/611#issuecomment-3072175559
This commit is contained in:
Thireus ☠
2025-07-16 13:11:19 +01:00
committed by GitHub
parent d3ed217798
commit da38486de5
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
ggml/include/ggml.h
View File

@@ -234,7 +234,12 @@
#define GGML_MAX_DIMS 4
#define GGML_MAX_PARAMS 2048
#define GGML_MAX_CONTEXTS 64
#ifndef GGML_MAX_CONTEXTS
// Maximum number of model contexts (e.g., for model shards).
// Increase this value using -DGGML_MAX_CONTEXTS=<value> in CMake
// if you need to load more than 64 model shards.
#define GGML_MAX_CONTEXTS 64
#endif
#define GGML_MAX_SRC 10
#ifndef GGML_MAX_NAME
#define GGML_MAX_NAME 64