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

4
modules/loaders.py
View file

@ -43,7 +43,8 @@ loaders_and_params = OrderedDict({
'compress_pos_emb',
'cpu',
'numa',
'no_offload_kqv'
'no_offload_kqv',
'tensorcores',
],
'llamacpp_HF': [
'n_ctx',
@ -65,6 +66,7 @@ loaders_and_params = OrderedDict({
'no_use_fast',
'logits_all',
'no_offload_kqv',
'tensorcores',
'llamacpp_HF_info',
],
'ExLlamav2_HF': [