text-generation-inference
https://github.com/huggingface/text-generation-inference
Python
Large Language Model Text Generation Inference
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to text-generation-inference
Help out
- Issues
- launch TGI with the argument `--max-input-tokens` smaller than sliding_window=4096 (got here max_input_tokens=16384)
- Bi-gram Repetation Penalty for the TGI configuration
- Unable to load/run LoRA Adapters on llama - 7B
- TGI crashes while loading Qwen2-VL-7B-Instruct
- Python client: Pydantic protected namespace "model_"
- detokenize
- Is there a way to defines "bad_words"?
- CUDA Error: No kernel image is available for execution on the device
- TGI Server should be installable via pip
- Complexe response format lead the container to run forever on CPU
- Docs
- Python not yet supported