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

Enable NUMA feature for llama_cpp_python (#4040)

Browse source
This commit is contained in:
StoyanStAtanasov 2023-09-27 03:05:00 +02:00 • committed by GitHub
parent 87ea2d96fd
commit 7e6ff8d1f0
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 21 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -125,6 +125,7 @@ parser.add_argument('--n-gpu-layers', type=int, default=0, help='Number of layer
parser.add_argument('--tensor_split', type=str, default=None, help="Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17")
parser.add_argument('--n_ctx', type=int, default=2048, help='Size of the prompt context.')
parser.add_argument('--llama_cpp_seed', type=int, default=0, help='Seed for llama-cpp models. Default 0 (random)')
parser.add_argument('--numa', action='store_true', help='Activate NUMA task allocation for llama.cpp')
# GPTQ
parser.add_argument('--wbits', type=int, default=0, help='Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.')