kingbri 2f568ff573 Config: Expose auto GPU split reserve config ...

The GPU reserve is used as a VRAM buffer to prevent GPU overflow
when automatically deciding how to load a model on multiple GPUs.
Make this configurable.

Signed-off-by: kingbri <bdashore3@proton.me>

2024-02-08 22:09:50 -05:00

..

chat_completion.py

API: Add logprobs for chat completions

2024-02-08 21:26:53 -05:00

common.py

Model: Add logprobs support

2024-02-08 21:26:53 -05:00

completion.py

Model: Add logprobs support

2024-02-08 21:26:53 -05:00

lora.py

Tree: Refactor code organization

2024-01-25 00:15:40 -05:00

model.py

Config: Expose auto GPU split reserve config

2024-02-08 22:09:50 -05:00

sampler_overrides.py

API: Add sampler override switching

2024-01-25 00:15:40 -05:00

template.py

API: Add template switching and unload endpoints

2024-01-25 00:15:40 -05:00

token.py

Tree: Refactor code organization

2024-01-25 00:15:40 -05:00