make
This commit is contained in:
parent
4b6e344bad
commit
22804439d2
2 changed files with 4 additions and 2 deletions
|
@ -1,8 +1,10 @@
|
|||
import subprocess
|
||||
import runpod
|
||||
import os
|
||||
import time
|
||||
|
||||
sleep_time = int(os.environ.get('SLEEP_TIME', 1))
|
||||
llama_cmd = os.environ.get('LLAMA_CMD', "/server --host 0.0.0.0 --threads 8 -ngl 999 -np 8 -cb -m model.gguf -c 16384")
|
||||
subprocess.Popen(llama_cmd.split(' '))
|
||||
|
||||
## load your model(s) into vram here
|
||||
|
||||
|
|
|
@ -27,7 +27,7 @@ ENV LLAMA_CUDA_MMV_Y=2
|
|||
ENV LLAMA_CUDA_DMMV_X=64
|
||||
ENV LLAMA_CUDA_F16=true
|
||||
|
||||
RUN make -j
|
||||
RUN make
|
||||
|
||||
# Accept the build argument into an environment variable
|
||||
ARG MODEL_URL
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue