CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-06 09:46:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : more graceful error handling of invalid session files

Browse Source 
* llama : remove LLAMA_MAX_RNG_STATE

It's no longer necessary to limit the size of the RNG state,
because the max size of session files is not estimated anymore.
This commit is contained in:
Francis Couture-Harpin
2024-07-27 14:31:57 -04:00
parent 83e6a17ddf
commit ffd5117def
2 changed files with 82 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/llama.h
View File

@@ -33,8 +33,6 @@
#define LLAMA_DEFAULT_SEED 0xFFFFFFFF
#define LLAMA_MAX_RNG_STATE (64*1024)
#define LLAMA_FILE_MAGIC_GGLA 0x67676c61u // 'ggla'
#define LLAMA_FILE_MAGIC_GGSN 0x6767736eu // 'ggsn'
#define LLAMA_FILE_MAGIC_GGSQ 0x67677371u // 'ggsq'