Bump llama-cpp-python to 0.2.24 (#5001)

This commit is contained in:
oobabooga 2023-12-19 15:22:21 -03:00 committed by GitHub
parent 83cf1a6b67
commit 0a299d5959
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
15 changed files with 104 additions and 96 deletions

View file

@ -115,6 +115,7 @@ def create_ui():
shared.gradio['mlock'] = gr.Checkbox(label="mlock", value=shared.args.mlock)
shared.gradio['numa'] = gr.Checkbox(label="numa", value=shared.args.numa, info='NUMA support can help on some systems with non-uniform memory access.')
shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu)
shared.gradio['no_offload_kqv'] = gr.Checkbox(label="no_offload_kqv", value=shared.args.no_offload_kqv, info='Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.')
shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit)
shared.gradio['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16)
shared.gradio['auto_devices'] = gr.Checkbox(label="auto-devices", value=shared.args.auto_devices)