mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2024-11-22 08:07:56 +01:00
ctransformers: add mlock and no-mmap options (#3649)
This commit is contained in:
parent
2da38e89e6
commit
e042bf8624
@ -19,7 +19,9 @@ class CtransformersModel:
|
||||
gpu_layers=shared.args.n_gpu_layers,
|
||||
batch_size=shared.args.n_batch,
|
||||
context_length=shared.args.n_ctx,
|
||||
stream=True
|
||||
stream=True,
|
||||
mmap=not shared.args.no_mmap,
|
||||
mlock=shared.args.mlock
|
||||
)
|
||||
|
||||
self.model = AutoModelForCausalLM.from_pretrained(
|
||||
|
@ -101,7 +101,9 @@ loaders_and_params = OrderedDict({
|
||||
'n_gpu_layers',
|
||||
'n_batch',
|
||||
'threads',
|
||||
'model_type'
|
||||
'model_type',
|
||||
'no_mmap',
|
||||
'mlock'
|
||||
]
|
||||
})
|
||||
|
||||
|
@ -42,4 +42,4 @@ https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_
|
||||
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||
|
||||
# ctransformers
|
||||
https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.22+cu117-py3-none-any.whl
|
||||
https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.23+cu117-py3-none-any.whl
|
||||
|
Loading…
Reference in New Issue
Block a user