mirror of
https://github.com/fauxpilot/fauxpilot.git
synced 2025-03-12 04:36:10 -07:00
The main change is that the model config format has changed. To deal with this we have a new script in the converter that will upgrade a model to the new version. Aside from that, we also no longer need to maintain our own fork of Triton since they have fixed the bug with GPT-J models. This should make it a lot easier to stay synced with upstream (although we still have to build our own container since there doesn't seem to be a prebuilt Triton+FT container hosted by NVIDIA). Newer Triton should let us use some nice features: - Support for more models, like GPT-NeoX - Streaming token support (this still needs to be implemented in the proxy though) - Dynamic batching Still TODO: - Proxy support for streaming tokens - Add stuff to setup.sh and launch.sh to detect if a model upgrade is needed and do it automatically.
6 lines
279 B
Docker
6 lines
279 B
Docker
FROM moyix/triton_with_ft:23.01
|
|
|
|
# Install dependencies: torch
|
|
RUN python3 -m pip install --disable-pip-version-check -U torch --extra-index-url https://download.pytorch.org/whl/cu116
|
|
RUN python3 -m pip install --disable-pip-version-check -U transformers bitsandbytes accelerate
|