vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

add --no-mmap in llama-bench (#5257)

Browse source 
* add --no-mmap, show sycl backend

* fix conflict

* fix code format, change print for --no-mmap

* ren no_mmap to mmap, show mmap when not default value in printer

* update guide for mmap

* mv position to reduce model reload
This commit is contained in:
Neo Zhang Jianyu 2024-02-02 03:48:53 +08:00 • committed by GitHub
parent 4d0924a890
commit 128dcbd3c9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 89 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

2
README-sycl.md
View file

@ -405,7 +405,7 @@ Using device **0** (Intel(R) Arc(TM) A770 Graphics) as main device
llama.cpp use mmap as default way to read model file and copy to GPU. In some system, memcpy will be abnormal and block.
Solution: add **--no-mmap**.
Solution: add **--no-mmap** or **--mmap 0**.
## Q&A