aphrodite-engine
https://github.com/pygmalionai/aphrodite-engine
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.
not yet supported1 Subscribers
Add a CodeTriage badge to aphrodite-engine
Help out
- Issues
- [Feature]: Consider integrating SVDquant (W4A4 quantization) from Nunchaku project
- [Bug]:Can't use speculative decoding
- [Kernel] Add support for FLUTE quantization
- [Bug]: Can't seem to disable enforcement of Eager mode.
- [Bug]: clamp broken with HIP
- [Feature]: Automatic max-model-len or max-num-seqs
- tokenizer: allow skip_special_tokens=False for mistral tokenizer
- [Usage]: Any tips on troubleshooting Quant-LLM
- [Bug]: Docker latest [FATAL tini (19)] exec /app/aphrodite-engine/docker/entrypoint.sh failed: No such file or directory
- [Bug]: FP8 KV Cache FLASHINFER AssertionError
- Docs
- not yet supported