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 supported4 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: CUDA OOM (due to flaky profiler?)
- [Performance]: Why is Llama 3.1 405B 5 times faster than 70B on benchmarks?
- [Bugfix][Hardware][Neuron] Fix getting version of neuronxcc
- [Misc]: Missing cu118 wheels for 0.6.2 release
- [Feature]: Pipeline Parallelism support for LLaMA3.2 90B Vision Model
- [Speculative Decoding]: Shard draft model over multiple GPUs
- [Bug]: Unable to load the tokenizers of certain models
- [Installation]: RISC-V support?
- [New Model]: Add support for Ovis models
- [Usage]: Serving Llama 3.2 `llama-3-2-11b-vision-instruct` hangs
- Docs
- Python not yet supported