vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: How to output logprob for each possiable token about classification or determin task?
- [Bug]: JAMBA 1.5 - Beam Search Returns a few characters then stops early
- [Bug]: Mismatch in TTFT count and number of successful requests completed
- [Performance]: Llama 3 70B; vLLM does not scale beyond TP=4
- [Bug]: vLLM 0.5.5 and FlashInfer0.1.6
- [Performance]: Too slow when serving for large number of prompts.
- [Bug]: dtype float16 Failure to use enable-chunked-prefill
- [New Model]: ValueError: Model architectures ['UltravoxModel'] are not supported for now.
- [Installation]: Using Image to build from source get error
- [Usage]: Does VLLM support starting multiple cards using mpirun? Want to bind different CPUs to each card.
- Docs
- Python not yet supported