Mozilla-Ocho / llamafile

Distribute and run LLMs with a single file.
https://llamafile.ai
Other
20.53k stars 1.03k forks source link

update GGML_HIP_UMA #536

Open Djip007 opened 3 months ago

Djip007 commented 3 months ago

add the 2 changes needed for llamafile:

Note: with linux kernel 6.10+ hip_malloc use GGT memory for some APU (Ryzen 7940HS ...) so the limite size is easly configurable on linux with boot parameter. No more need for BIOS VRAM change.

#add at boot kernel param to have 16Go of GGT Memory. (default is 1/2 of free RAM)
amdgpu.gttsize=16384 

Note2: With this patch/UMA we can use all RAM without config.

(https://github.com/Mozilla-Ocho/llamafile/issues/439#issuecomment-2266253187 update)