Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2025-01-27 12:33:17 +01:00
Code Issues Packages Projects Releases Wiki Activity

Improve the --help message about --tensorcores as well

Browse Source
This commit is contained in:
oobabooga 2025-01-10 07:07:41 -08:00
parent da6d868f58
commit 7fe46764fb
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
modules/shared.py
View File

@ -116,7 +116,7 @@ group.add_argument('--quant_type', type=str, default='nf4', help='quant_type for
# llama.cpp
group = parser.add_argument_group('llama.cpp')
group.add_argument('--flash-attn', action='store_true', help='Use flash-attention.')
group.add_argument('--tensorcores', action='store_true', help='NVIDIA only: use llama-cpp-python compiled with tensor cores support. This may increase performance on newer cards.')
group.add_argument('--tensorcores', action='store_true', help='NVIDIA only: use llama-cpp-python compiled without GGML_CUDA_FORCE_MMQ. This may improve performance on newer cards.')
group.add_argument('--n_ctx', type=int, default=2048, help='Size of the prompt context.')
group.add_argument('--threads', type=int, default=0, help='Number of threads to use.')
group.add_argument('--threads-batch', type=int, default=0, help='Number of threads to use for batches/prompt processing.')