Bump back llama-cpp-python (#6257)

This commit is contained in:
oobabooga 2024-07-22 16:19:41 -03:00 committed by GitHub
parent 0f53a736c1
commit 11bbf71aa5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 45 additions and 109 deletions

View file

@ -118,7 +118,6 @@ 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='Use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards. NVIDIA only.')
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.')
@ -217,6 +216,7 @@ group.add_argument('--model_type', type=str, help='DEPRECATED')
group.add_argument('--pre_layer', type=int, nargs='+', help='DEPRECATED')
group.add_argument('--checkpoint', type=str, help='DEPRECATED')
group.add_argument('--monkey-patch', action='store_true', help='DEPRECATED')
group.add_argument('--tensorcores', action='store_true', help='DEPRECATED')
args = parser.parse_args()
args_defaults = parser.parse_args([])