fauxpilot / fauxpilot

FauxPilot - an open-source alternative to GitHub Copilot server

fauxpilot/fauxpilot Issues

Python backend - fauxpilot-copilot_proxy failed to connect to all addresses
Updated 11 days ago8
I try to use VSCode Copilot plugin by edit settings.json, but it seems that no requests have been sent to my local server
Closed a month ago6
Support for StarCoder
Updated 15 days ago1
CodeGen2 compatibility
Updated 17 days ago3
Do you have a client plugin for idea?
Updated 25 days ago2
Support for the new replit-code-v1-3b model
Updated a month ago
failed to connect to all addresses
Closed 3 months ago5
openai.error.APIError while running client API example
Updated a month ago5
Does fauxpilot support adding our own data set for finetuning？ Thank you！
Updated a month ago1
Can i add some other models to fauxpilot except codegen series, like gpt-neo.
Updated a month ago3
How to run multiple models on one machine (w/ one GPU)
Updated a month ago4
See multiple warning when loading codegen weights
Updated a month ago6
How to install without docker?
Closed a month ago3
"[StatusCode.UNIMPLEMENTED] Received http2 header with status: 404" from fauxpilot-copilot_proxy-1
Updated a month ago1
fastertransformer not available
Updated a month ago7
Could this be used by a small team?
Closed 4 months ago8
Can you run it on CPU only?
Updated 2 months ago5
Minimum required gpu config
Closed 2 months ago3
fauxpilot in cuda 11.7
Updated 2 months ago1
RTX 4090 GPU is not yet supported in this version of the container
Updated 2 months ago4
`nvidia-docker` really required?
Closed 2 months ago2
I get an error at ./launch it starts the triton server and then says it cand find a GPU?
Updated 2 months ago2
Minimum requirements?
Updated 2 months ago4
Use fastertransformer backend with fp16?
Updated 2 months ago3
Triton cannot find config.pbtxt
Updated 2 months ago12
Support TensorRT backend
Updated 2 months ago2
Issues launching when using WSL2
Closed 2 months ago2
Add 8bit and int4 inference support to run larger models with less VRAM
Updated 2 months ago1
bug: setup.sh generates the "integer expression expected" issue.
Closed 3 months ago
CUDA runtime error : out of memory
Updated 3 months ago1
bug: incorrect if statement to compare between docker versions
Updated 3 months ago
'NoneType' object has no attribute 'squeeze'
Updated 3 months ago2
My inference time is over 40 seconds on an rtx 2060 12gb with codegen 2B. Is this normal?
Closed 3 months ago4
[feature request] basic gitlab setup instructions
Closed 3 months ago4
mpirun error
Updated 3 months ago2
Due to the Python backend, FauxPilot returns an inference error.
Closed 4 months ago6
How best to fork and edit the backend container logic
Closed 4 months ago2
1
Closed 5 months ago
Empty Results; proxy server: "failed to connect on all addresses"
Closed 5 months ago11
Add contrastive search sampler
Closed 5 months ago7
Can you share your server?I want it but I haven't got a computer was eligible.
Closed 5 months ago3
-d (daemon) is optional among ther docker-compose version
Closed 5 months ago
[python-backend] Allow more models
Updated 5 months ago4
Proposal: An efficient repo management for FauxPilot community
Closed 5 months ago3
> I don't see anything obvious in the log files. I did just fix a bug related to an environment variable ([e153c17](https://github.com/moyix/fauxpilot/commit/e153c17194423cb4a010b858d5483052f6fe6bbb)) so could you give a try with the most recent git version?
Closed 6 months ago
[BUG] Always got empty result
Closed 6 months ago2
How to build my own dataset to fine-tune the model
Closed 6 months ago1
Bug: non-default `TRITON_PORT` in `./setup.sh` fails to edit `docker-compose.yaml`
Closed 6 months ago
No supported GPU(s) detected to run this container
Closed 6 months ago1
model_convert
Closed 7 months ago1