llama.cpp
32c54116
- Revert "Support using mmap when applying LoRA (#2095)" (#2206)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
Revert "Support using mmap when applying LoRA (#2095)" (#2206) Has perf regression when mlock is used. This reverts commit 2347463201a9f4159ae95b737e1544dd300569c8.
References
#2206 - Revert "Support using mmap when applying LoRA (#2095)"
Author
howard0su
Parents
ff5d58fa
Loading