mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add llama-cpp-python wheels with tensor cores support (#5003)

Browse source
This commit is contained in:
oobabooga 2023-12-19 17:30:53 -03:00 • committed by GitHub
parent 0a299d5959
commit de138b8ba6
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
9 changed files with 69 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

13
modules/llamacpp_model.py
View file

@ -19,12 +19,21 @@ try:
except:
llama_cpp_cuda = None
try:
import llama_cpp_cuda_tensorcores
except:
llama_cpp_cuda_tensorcores = None
def llama_cpp_lib():
if (shared.args.cpu and llama_cpp is not None) or llama_cpp_cuda is None:
if shared.args.cpu and llama_cpp is not None:
return llama_cpp
else:
elif shared.args.tensorcores and llama_cpp_cuda_tensorcores is not None:
return llama_cpp_cuda_tensorcores
elif llama_cpp_cuda is not None:
return llama_cpp_cuda
else:
return llama_cpp
def ban_eos_logits_processor(eos_token, input_ids, logits):