tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-21 23:22:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

ggml : reduce hash table reset cost (#8698)

Browse Source 
* ggml : reduce hash table reset cost

* fix unreachable code warnings after GGML_ASSERT(false)

* GGML_ASSERT(false) -> GGML_ABORT("fatal error")

* GGML_ABORT use format string
This commit is contained in:
slaren
2024-07-27 04:41:55 +02:00
committed by GitHub
parent 01245f5b16
commit 2b1f616b20
46 changed files with 851 additions and 754 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/tokenize/tokenize.cpp
View File

@@ -163,7 +163,7 @@ static void write_utf8_cstr_to_stdout(const char * str, bool & invalid_utf8) {
printf(">");
return;
}
GGML_ASSERT(false && "MultiByteToWideChar() failed in an unexpected way.");
GGML_ABORT("MultiByteToWideChar() failed in an unexpected way.");
}
LPWSTR wstr = (LPWSTR) calloc(length_needed+1, sizeof(*wstr));