happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

mmap: add Haiku support by skipping RLIMIT_MEMLOCK check (#18819) 

Haiku OS does not support RLIMIT_MEMLOCK, similar to visionOS/tvOS.
Skip the resource limit check on Haiku to allow mlock functionality
to work without compile errors.

Tested on Haiku with NVIDIA RTX 3080 Ti using Vulkan backend.
This commit is contained in:
Daniel Benjaminsson 2026-01-14 08:11:05 +01:00 committed by GitHub
parent f709c7a33f
commit d34aa07193
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/llama-mmap.cpp
View File

@ -614,9 +614,9 @@ struct llama_mlock::impl {
char* errmsg = std::strerror(errno);
bool suggest = (errno == ENOMEM);
#if defined(TARGET_OS_VISION) || defined(TARGET_OS_TV) || defined(_AIX)
// visionOS/tvOS dont't support RLIMIT_MEMLOCK
// Skip resource limit checks on visionOS/tvOS
#if defined(TARGET_OS_VISION) || defined(TARGET_OS_TV) || defined(_AIX) || defined(__HAIKU__)
// visionOS/tvOS/Haiku don't support RLIMIT_MEMLOCK
// Skip resource limit checks on these platforms
suggest = false;
#else
struct rlimit lock_limit;